CN109582762A - Data processing method and server - Google Patents
Data processing method and server Download PDFInfo
- Publication number
- CN109582762A CN109582762A CN201811123302.2A CN201811123302A CN109582762A CN 109582762 A CN109582762 A CN 109582762A CN 201811123302 A CN201811123302 A CN 201811123302A CN 109582762 A CN109582762 A CN 109582762A
- Authority
- CN
- China
- Prior art keywords
- interaction
- request
- layer
- interactive
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/163—Interprocessor communication
- G06F15/173—Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
- G06F15/17306—Intercommunication techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This specification embodiment provides a kind of data processing method and server.The described method includes: receiving interaction request；The interaction request is corresponding with interactive information；The interactive information is input to the Internet, obtains the corresponding interaction path of the interaction request；The Internet includes multiple data analysis layers with upstream-downstream relationship；The data analysis layer can export at least one processing result: the interaction path includes at least one processing result of at least one data analysis layer output；According to the interaction path, the corresponding interaction results of the interaction request are determined.
Description
Technical Field
The embodiment of the specification relates to the technical field of computers, in particular to a data processing method and a server.
Background
With the development of internet and communication technology, users can interactively ask and answer with a server to consult some questions and obtain corresponding answers. The interactive question answering may include at least one round of interactive process.
In the related art, a developer may pre-configure an interactive link of a tree structure at a server. In each round of interaction process, the server can determine an interaction path according to the interaction link to realize the interaction process. However, the actual service scenarios are very diverse, and in different service scenarios, the server implements the interaction process according to the same interaction link, and the interaction paths are the same. Therefore, the interaction time between the user and the server is long, and the interaction efficiency is low.
Disclosure of Invention
An object of the embodiments of the present specification is to provide a data processing method and a server, so as to reduce interaction duration and improve interaction efficiency.
In order to achieve the above object, an embodiment of the present specification provides a data processing method, including: receiving an interactive request; the interaction request corresponds to interaction information; inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer; and determining an interaction result corresponding to the interaction request according to the interaction path.
To achieve the above object, a data processing apparatus according to an embodiment of the present specification includes: a submitting mutual request receiving unit for receiving the mutual request; the interaction request corresponds to interaction information; an interaction path determining unit, configured to input the interaction information to an interaction network, so as to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer; and the interaction result determining unit is used for determining an interaction result corresponding to the interaction request according to the interaction path.
To achieve the above object, an embodiment of the present specification provides a server, including: a memory for storing computer instructions; a processor for executing the computer instructions to perform the steps of: receiving an interactive request; the interaction request corresponds to interaction information; inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer; and determining an interaction result corresponding to the interaction request according to the interaction path.
As can be seen from the technical solutions provided in the embodiments of the present specification, the intelligent question answering server may receive an interaction request, where the interaction request corresponds to interaction information; the interaction information can be input into an interaction network to obtain an interaction path corresponding to the interaction request; and determining an interaction result corresponding to the interaction request according to the interaction path. Therefore, the intelligent question-answering server can flexibly determine the interaction path according to the interaction network, thereby reducing the interaction time length and improving the interaction efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a flow chart of a data processing method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an interactive network according to an embodiment of the present disclosure;
fig. 3 is a functional structure diagram of a server according to an embodiment of the present disclosure;
fig. 4 is a functional structure diagram of a server according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.
Please refer to fig. 1 and fig. 2. The embodiment of the specification provides a data processing method. The data processing method can take the intelligent question-answering server as an execution subject. The intelligent question-answering server can be an Interactive Voice Response (IVR) server, an intelligent chat robot server, or the like. The intelligent question and answer server can be one server or a server cluster comprising a plurality of servers.
In this embodiment, the intelligent question and answer server can perform interactive question and answer with the user. The interactive question answering may include at least one round of interactive process. Specifically, the intelligent question and answer server can receive an interactive request from a user; an interaction result corresponding to the interaction request may be obtained. The intelligent question and answer server can judge whether a new round of interaction process needs to be started according to the interaction result. If yes, the intelligent question-answering server can generate a new interactive request; a new interaction result corresponding to the new interaction request may be obtained. If not, the intelligent question-answering server does not interact with the user any more; the interaction result may be provided to a downstream service channel for processing by the downstream service channel. For example, when the interaction result is continuous interaction, the intelligent question and answer server may determine that a new round of interaction process needs to be started; and when the interaction result is the end of the interaction, the intelligent question-answering server can judge that a new round of interaction process is not required to be started. In addition, after each round of interaction process is finished, the intelligent question-answering server can also provide guidance words for the user according to the interaction result of the round of interaction process. For example, when the interaction result is continuous interaction, the guidance language may be "please confirm that the question of your consultation is XXX", "ask what the XXX question of your consultation is about"; when the interaction result is ending interaction, the guidance language can be "manual service for you has been transferred" or "hang up".
In this embodiment, the intelligent question and answer server may provide an interactive network. The interactive network can be a network model preset by a developer, and can realize interaction with a user. The interaction network may include a plurality of data processing layers having an upstream and downstream relationship. Each data processing layer is capable of outputting one or more processing results. The data processing layer can comprise at least one of an interaction type recognition layer, an interaction intention recognition layer, an interaction action response layer and an interaction result output layer. The interaction type identification layer may be configured to identify a request type corresponding to the interaction request. The interaction intention identification layer can be used for identifying user requirements corresponding to the interaction requests. The interaction response layer may be configured to generate a response action corresponding to the interaction request. The interaction result output layer can be used for generating an interaction result corresponding to the interaction request.
Specifically, the interaction type identification layer may correspond to a plurality of request types, and the processing result output by the interaction type identification layer may include at least one of the plurality of request types. The request types may include, for example, a first-turn type, an agreement type, an objection type, a no-reply type, a description type, and the like. The first-wheel type is used for indicating that the number of wheels corresponding to the interactive process is a first wheel. The consent type is used to indicate user consent to the user requirements identified during the last round of interaction. The objection type is used for representing that the user object to the user requirements identified in the last round of interaction process. The no-answer type indicates that the user has not answered positively to the user's needs identified during the previous round of interaction. The description type indicates that the user is describing the requirement. Specifically, the first-round type may include, for example, "new call" or the like, where the "new call" is used to indicate that the user calls for the first time. The consent type may include, for example, "yes" or the like. The objection type may include, for example, "no," etc. The no-reply type may include, for example, "small talk", "silent", "find manual service", etc., which indicates that the user requires to switch to manual service. The description types may include, for example, "yes _ other," "no _ other," "other," and so forth.
Specifically, the interaction intention recognition layer may correspond to a plurality of user requirement generation algorithms, and the processing result output by the interaction intention recognition layer may include a processing result of at least one of the plurality of user requirement generation algorithms. The user demand generation algorithm may include, for example, a speculation algorithm, an identification algorithm, a supplemental algorithm, and the like. The inference algorithm may be used to infer user requirements, for example, user requirements may be inferred from user behavior information. The identification algorithm may be used to identify user requirements, for example, user requirements may be identified based on user input information. The supplemental algorithm may be used to generate supplemental information to ask a user back when the user's input information is incomplete in the hope of the user supplementing it. The supplementation algorithm may generate information to be supplemented, for example, based on input information from a user. The inference algorithm, the recognition algorithm, and the complementary algorithm may be implemented in any manner, such as machine learning, and the like. The input information about the behavior information will be described in detail in the following process.
The interaction response layer may correspond to a plurality of response actions, and the processing result output by the interaction response layer may include at least one of the plurality of response actions. The response action may include, for example, a guidance description, a guidance confirmation, and the like. The guide description may be used to guide the user in describing the requirements. The boot confirmation may be used to guide the user to confirm whether the identified user requirement is correct.
The interaction result output layer can correspond to various interaction results. The processing result output by the interaction result output layer may include at least one of the plurality of interaction results. The interaction result may include, for example, continuing the interaction, ending the interaction, and so on. And the continuous interaction means ending the current round of interaction process and starting a new round of interaction process. The end interaction means to end the current round of interaction but not start a new round of interaction process. The ending interaction may include, for example, "output asked questions," "output bottomed," and so on. The "output question" means that the current round of interaction is ended and a question is provided to a downstream service channel, and the question can be understood as an advisory question with a canonical format. The output of the output bag bottom means that the current round of interaction is ended and other information is provided for the downstream service channel.
In this embodiment, the interaction network may correspond to constraint rules. The constraint rule may be used to constrain a link relationship between processing results output by the plurality of data processing layers. As previously mentioned, the interaction network may include a plurality of data processing layers having an upstream and downstream relationship. In this way, in the constraint rule, the processing results output by the interaction type identification layer may have a link relationship with the processing results output by the interaction intention identification layer, the interaction action response layer, and the interaction result output layer, respectively. The processing result output by the interaction intention recognition layer can respectively have a link relation with the processing results output by the interaction action response layer and the interaction result output layer; the processing result output by the interaction response layer may have a link relationship with the processing result output by the interaction result output layer. In addition, each link relation may correspond to a satisfaction condition; when the condition is satisfied, the link relation can be established.
For example, the interaction type identification layer may correspond to a plurality of request types such as a first-round type, an agreement type, an objection type, a no-answer type, a description type, and the like; the processing result output by the interaction type recognition layer may include at least one of the plurality of request types. The interaction intention identification layer can correspond to various user requirement generation algorithms such as a prediction algorithm, an identification algorithm, a supplement algorithm and the like; the processing result output by the interaction intention recognition layer may include a processing result of at least one user requirement generation algorithm of the plurality of user requirement generation algorithms. The interactive action response layer can correspond to various response actions such as guidance description, guidance confirmation and the like; the processing result output by the interactive action response layer may include at least one of the plurality of response actions. The interaction result output layer can correspond to various interaction results such as continuous interaction, ending interaction and the like; the processing result output by the interaction result output layer may include at least one of the plurality of interaction results.
Then, in the constraint rule, the first-round type may have a link relationship with the processing result of the inference algorithm and the ending interaction; the consent type may have a linking relationship with the guidance description, and the ending interaction; the objection type may have a link relationship with the guidance description, and the ending interaction; the no-reply type may have a linking relationship with the guidance confirmation, the guidance description, and the ending interaction; the description type may have a link relationship with a processing result of the recognition algorithm, a processing result of the complementary algorithm, and the ending interaction. In the constraint rule, the processing result of the speculative algorithm may have a link relation with the boot confirmation and the boot description; the processing result of the recognition algorithm can have a link relation with the guide confirmation and the guide description; the processing result of the complementary algorithm may have a linking relationship with the guidance description, the ending interaction. In the constraint rule, the guiding confirmation can have a link relation with the continuous interaction; the guidance description may have a linking relationship with the continued interaction.
In the constraint rule, the condition corresponding to the link relationship between the first-round type and the processing result of the inference algorithm may include, for example: the interactive question and answer times of the user and the intelligent question and answer server within 1 day are less than a preset value. The condition corresponding to the link relationship between the first-round type and the ending interaction may include, for example: the interactive question and answer times of the user and the intelligent question and answer server within 1 day are more than or equal to a preset value. Of course, other link relationships in the constraint rule may also correspond to conditions, which are not listed here.
The data processing method of this embodiment may correspond to any round of interactive process in the interactive question-answering, and specifically may include the following steps.
Step S10: an interactive request is received.
In this embodiment, the interaction request may correspond to interaction information. The interaction information may include at least one of: the method comprises the following steps of behavior information of a user, state information of the user, input information of the user, a processing result of a data processing layer in the previous round of interaction process and interaction parameters corresponding to the round of interaction process. The behavior information may be used to describe the behavior of the user, and may include, for example, the number of times the user performs interactive questioning and answering with the intelligent questioning and answering server within a specific time period, behavior data such as "login", "transfer", "payment" of the user, and help information of the user in other channels (e.g., stapling, vigorous energy, etc.). The status information may be used to describe the status of the user, and may include, for example, whether the user is a vip (veryimportant person) user, or the like. The input information may include information input by the user in the current round of interaction process and its Context (Context). The information input by the user in the round of interaction process may include, for example, "yes", "not, how to open the flower", "pay for the treasures", "account stolen", and the like. User silence is also understood here as an input information. The input information may be any form of information, such as voice information, text information, or image information. The interaction parameters may include, for example, the number of rounds corresponding to the current round of interaction process.
The number of rounds corresponding to the interaction process in this embodiment may be the first round. The interactive request may be sent by the terminal device. The terminal device may be, for example, a fixed telephone, a mobile telephone (e.g., a smart phone, a feature machine, etc.), a tablet electronic device, a portable computer, a Personal Digital Assistant (PDA), a server, an industrial personal computer (industrial control computer), a Personal Computer (PC), a kiosk, or the like. Specifically, the terminal device may receive an interactive instruction from a user; an interactive request may be sent to the smart question and answer server. The interaction request may carry user identification information. The user identification information may be used to identify a user, and may be, for example, a mobile phone number, a mailbox address, or the like. The intelligent question and answer server can receive the interactive request; behavior information and/or state information of the user can be acquired according to the user identification information and used as interaction information corresponding to the interaction request. Further, the interaction request may also carry input information of the user. The intelligent question-answering server can also take the input information as the interactive information corresponding to the interactive request.
For example, the terminal device may be run with an intelligent dialog tool. The intelligent dialog tool may be a computer program that enables instant interaction with a user. The intelligent dialog tool may be, for example, intelligent customer service, mini-ice from microsoft corporation, tomb corporation, JIMI from kyoto corporation, waiwas, Siri from apple corporation, or the like. The intelligent dialog tool may be provided with a session interface and a send control. The user can input information in the session interface; the send control may be triggered. After detecting that the sending control is triggered, the terminal device considers that an interaction instruction from a user is received; an interaction request may be sent to the intelligent question-answering server, where the interaction request carries the user identification information of the user.
As another example, the terminal device may have a telephone dialing function. And the user can use the terminal equipment to dial the service telephone corresponding to the intelligent question-answering server. After detecting that a user dials a service telephone, the terminal equipment considers that an interaction instruction from the user is received; an interactive request (call request) may be sent to the smart question and answer server. The intelligent question and answer server can receive the call request; the incoming call number may be used as the user identification information.
Of course, the number of rounds corresponding to the interaction process in this embodiment may also be not the first round, for example, the 2 nd round, the 3 rd round, and the like. The interactive requests may be generated by the smart question and answer server. For convenience of description, the previous round of the interaction process of the embodiment may be taken as the first interaction process; the interactive process of the present embodiment may be taken as the second interactive process. The intelligent question-answering server can judge that a second interactive process needs to be started according to the interactive result of the first interactive process; and an interaction request of the second interaction process can be generated. The intelligent question-answering server may use a processing result of the data processing layer in the first interaction process as interaction information corresponding to the interaction request in the second interaction process. Further, the intelligent question and answer server can also receive input information from a user in the second interaction process; the input information may be used as the interaction information corresponding to the interaction request in the second interaction process.
Step S12: and inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request.
In this embodiment, as mentioned above, the interaction network may correspond to constraint rules. In this way, the intelligent question and answer server may input the interaction information to the interaction network, so that the interaction network generates an interaction path according to the link relationship constrained by the constraint rule. The interaction path may include at least the processing result output by the interaction type identification layer and the interaction result output layer. Of course, the interaction path may also include the processing result output by the interaction intention recognition layer and/or the interaction action response layer.
In an implementation manner of this embodiment, the interaction type identification layer may select one request type from multiple corresponding request types as a request type corresponding to the interaction request according to the interaction information; determining that the processing result linked by the request type comes from the interaction result output layer according to the constraint rule; the request type may be sent to the interaction result output layer. The interaction result output layer can receive the request type; according to the constraint rule, one interactive result can be selected from the multiple interactive results as the interactive result corresponding to the interactive request. Thus, the request type selected by the interaction type identification layer and the interaction result selected by the interaction result output layer can form an interaction path.
For example, the interaction information may include behavior information of the user and interaction parameters corresponding to the current round of interaction process. The behavior information may include the number of times the user has interacted with the smart question-and-answer server within 1 day. The number of times may be greater than or equal to a preset value. The interaction parameter may include the number of turns corresponding to the current round of interaction process. The number of wheels may be 1.
In the constraint rule, the first-round type may have a link relationship with a processing result of the inference algorithm and the end interaction. The condition corresponding to the link relationship between the first-wheel type and the ending interaction may include: the interactive question and answer times of the user and the intelligent question and answer server within 1 day are more than or equal to a preset value. The condition corresponding to the link relationship between the first-round type and the processing result of the inference algorithm may include: the interactive question and answer times of the user and the intelligent question and answer server within 1 day are less than a preset value.
Then, the interaction type identification layer may select a first round type from the multiple corresponding request types as a request type corresponding to the interaction request according to the interaction information; determining that the processing result linked by the request type comes from the interaction result output layer according to the constraint rule; the request type may be sent to the interaction result output layer. The interaction result output layer can receive the request type; and selecting the finishing interaction from the corresponding multiple interaction results as the interaction result corresponding to the interaction request according to the constraint rule.
In another implementation manner of this embodiment, the interaction type identification layer may select one request type from multiple corresponding request types as a request type corresponding to the interaction request according to the interaction information; determining that the processing result linked by the request type comes from the interaction intention identification layer according to the constraint rule; the interactive information and the request type may be transmitted to the interactive result output layer. The interaction intention identification layer can receive interaction information and the request type; selecting one user requirement generating algorithm from multiple corresponding user requirement generating algorithms according to the constraint rule; the interactive information can be processed by using a selected user requirement generation algorithm to obtain a processing result; determining that the processing result linked by the processing result comes from the interaction result output layer according to the constraint rule; the processing result may be sent to the interaction result output layer. The interaction result output layer can receive the processing result; according to the constraint rule, one interactive result can be selected from the multiple interactive results as the interactive result corresponding to the interactive request. Thus, the request type selected by the interaction type identification layer, the processing result output by the transaction intention identification layer and the interaction result selected by the interaction result output layer can form an interaction path.
In another implementation manner of this embodiment, the interaction type identification layer may select one request type from multiple corresponding request types as a request type corresponding to the interaction request according to the interaction information; determining that the processing result linked by the request type comes from the interactive action response layer according to the constraint rule; the request type may be sent to the interactivity response layer. The interactivity response layer may receive the request type; selecting one response action from the corresponding multiple response actions as the response action corresponding to the interaction request according to the constraint rule; determining that the processing result linked by the response action is from the interaction result output layer according to the constraint rule; the response action may be sent to the interaction result output layer. The interaction result output layer may receive the response action; according to the constraint rule, one interactive result can be selected from the multiple interactive results as the interactive result corresponding to the interactive request. Therefore, the request type selected by the interactive type identification layer, the response action selected by the interactive action response layer and the interactive result selected by the interactive result output layer can form an interactive path.
In another implementation manner of this embodiment, the interaction type identification layer may select one request type from multiple corresponding request types as a request type corresponding to the interaction request according to the interaction information; determining that the processing result linked by the request type comes from the interaction intention identification layer according to the constraint rule; the interactive information and the request type may be transmitted to the interactive result output layer. The interaction intention identification layer can receive interaction information and the request type; selecting one user requirement generating algorithm from multiple corresponding user requirement generating algorithms according to the constraint rule; the interactive information can be processed by using a selected user requirement generation algorithm to obtain a processing result; determining that the processing result linked by the processing result comes from the interactive action response layer according to the constraint rule; the processing result may be sent to the interactivity response layer. The interactive action response layer may receive the processing result; selecting one response action from the corresponding multiple response actions as the response action corresponding to the interaction request according to the constraint rule; determining that the processing result linked by the response action is from the interaction result output layer according to the constraint rule; the response action may be sent to the interaction result output layer. The interaction result output layer may receive the response action; according to the constraint rule, one interactive result can be selected from the multiple interactive results as the interactive result corresponding to the interactive request. Thus, the request type selected by the interaction type identification layer, the processing result output by the transaction intention identification layer, the response action selected by the interaction action response layer and the interaction result selected by the interaction result output layer can form an interaction path.
Step S14: and determining an interaction result corresponding to the interaction request according to the interaction path.
In this embodiment, as described above, the interaction path may include at least the processing result output by the interaction type identification layer and the interaction result output layer. In this way, the intelligent question-answering server can obtain the processing result output by the interaction result output layer from the interaction path as the interaction result corresponding to the interaction request. Of course, the intelligent question-answering server may also obtain a processing result output by one or more other data processing layers from the interaction path, as an interaction result corresponding to the interaction request.
In an implementation manner of this embodiment, the interaction network may further include a preprocessing layer. The preprocessing layer, the interaction type recognition layer, the interaction intention recognition layer, the interaction response layer, and the interaction result output layer may have an upstream-downstream relationship in order. The preprocessing layer can be used for acquiring the interactive information corresponding to the interactive request.
In this embodiment, the intelligent question-answering server may receive an interaction request, where the interaction request corresponds to interaction information; the interaction information can be input into an interaction network to obtain an interaction path corresponding to the interaction request; and determining an interaction result corresponding to the interaction request according to the interaction path. Therefore, the intelligent question-answering server can flexibly determine the interaction path according to the interaction network, thereby reducing the interaction time length and improving the interaction efficiency.
Please refer to fig. 3. The embodiment of the specification provides a server. The server includes the following elements.
An interaction request receiving unit 20, configured to receive an interaction request; the interaction request corresponds to interaction information;
an interaction path determining unit 22, configured to input the interaction information to an interaction network, so as to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer;
and the interaction result determining unit 24 is configured to determine an interaction result corresponding to the interaction request according to the interaction path.
Please refer to fig. 4. The embodiment of the specification provides a server. The server may include a memory and a processor.
In the present embodiment, the Memory includes, but is not limited to, a Dynamic Random Access Memory (DRAM), a Static Random Access Memory (SRAM), and the like. The memory may be used to store computer instructions.
In this embodiment, the processor may be implemented in any suitable manner. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The processor may be configured to execute the computer instructions to perform the steps of: receiving an interactive request; the interaction request corresponds to interaction information; inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer; and determining an interaction result corresponding to the interaction request according to the interaction path.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Especially for the server embodiment, since it is basically similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
In addition, it is understood that one skilled in the art, after reading this specification document, may conceive of combinations of some or all of the embodiments recited in this specification document which are also within the scope of the disclosure and protection of this specification without the need for inventive faculty.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate a dedicated integrated circuit chip 2. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most popular applications. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
From the above description of the embodiments, it is clear to those skilled in the art that the present specification can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solutions of the present specification may be essentially or partially implemented in the form of software products, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments of the present specification.
The description is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
While the specification has been described with examples, those skilled in the art will appreciate that there are numerous variations and permutations of the specification that do not depart from the spirit of the specification, and it is intended that the appended claims include such variations and modifications that do not depart from the spirit of the specification.
Claims (12)
1. A method of data processing, comprising:
receiving an interactive request; the interaction request corresponds to interaction information;
inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer;
and determining an interaction result corresponding to the interaction request according to the interaction path.
2. The method of claim 1, the data processing layer comprises at least one of an interaction type recognition layer, an interaction intention recognition layer, an interaction action response layer, and an interaction result output layer; the interaction type identification layer is used for identifying a request type corresponding to the interaction request; the interaction intention identification layer is used for identifying user requirements corresponding to the interaction requests; the interaction action response layer is used for generating a response action corresponding to the interaction request; and the interaction result output layer is used for generating an interaction result corresponding to the interaction request.
3. The method of claim 2, wherein the interaction type identification corresponds to a plurality of request types; the processing result output by the interaction type identification layer comprises at least one of the multiple request types;
the interaction intention identification layer corresponds to a plurality of user requirement generation algorithms; the processing result output by the interaction intention recognition layer comprises the processing result of at least one user requirement generation algorithm in the multiple user requirement generation algorithms;
the interactive action response layer corresponds to a plurality of response actions; the processing result output by the interactive action response layer comprises at least one of the response actions;
the interaction result output layer corresponds to various interaction results; the processing result output by the interaction result output layer comprises at least one of the plurality of interaction results.
4. The method of claim 2, wherein the interaction path comprises at least the processing results output by the interaction type identification layer and the interaction result output layer.
5. The method of claim 4, the interaction path further comprising a processing result output by the interaction intent recognition layer and/or the interaction action response layer.
6. The method of claim 4 or 5, wherein the determining, according to the interaction path, an interaction result corresponding to the interaction request includes:
and acquiring the processing result output by the interaction result output layer from the interaction path as the interaction result corresponding to the interaction request.
7. The method of claim 1, the interaction network corresponds to a constraint rule; the constraint rule is used for constraining the link relation among the processing results output by the plurality of data processing layers.
8. The method of claim 7, wherein the inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request comprises:
and inputting the interaction information into an interaction network so that the interaction network generates an interaction path according to the link relation constrained by the constraint rule.
9. The method of claim 1, the interaction information comprising at least one of:
behavior information of the user;
status information of the user;
input information of a user;
processing results of the data processing layer in the previous round of interaction;
and (5) corresponding interaction parameters in the current round of interaction process.
10. The method of claim 1, the receiving an interactive request, comprising:
receiving an interactive request sent by terminal equipment; or,
and receiving the interactive request generated by the server.
11. A data processing apparatus comprising:
an interactive request receiving unit, configured to receive an interactive request; the interaction request corresponds to interaction information;
an interaction path determining unit, configured to input the interaction information to an interaction network, so as to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer;
and the interaction result determining unit is used for determining an interaction result corresponding to the interaction request according to the interaction path.
12. A server, comprising:
a memory for storing computer instructions;
a processor for executing the computer instructions to perform the steps of: receiving an interactive request; the interaction request corresponds to interaction information; inputting the interaction information into an interaction network to obtain an interaction path corresponding to the interaction request; the interactive network comprises a plurality of data processing layers having an upstream and downstream relationship; the data processing layer can output at least one processing result: the interaction path comprises at least one processing result output by at least one data processing layer; and determining an interaction result corresponding to the interaction request according to the interaction path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811123302.2A CN109582762A (en) | 2018-09-26 | 2018-09-26 | Data processing method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811123302.2A CN109582762A (en) | 2018-09-26 | 2018-09-26 | Data processing method and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109582762A true CN109582762A (en) | 2019-04-05 |
Family
ID=65919905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811123302.2A Pending CN109582762A (en) | 2018-09-26 | 2018-09-26 | Data processing method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109582762A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119293190A (en) * | 2024-11-11 | 2025-01-10 | 暗物质(北京)智能科技有限公司 | Interaction method, device and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1280315A1 (en) * | 1992-07-31 | 2003-01-29 | Micron Technology, Inc. | Apparatus and method for providing network security |
| JP2004172781A (en) * | 2002-11-19 | 2004-06-17 | Hitachi Ltd | Information processing apparatus for voice interaction, voice interaction processing system, and car navigation terminal |
| EP1443425A1 (en) * | 2003-01-29 | 2004-08-04 | Hewlett-Packard Company, A Delaware Corporation | Process for maintenance of a repository of documents and system for doing the same |
| US20040174981A1 (en) * | 2003-03-04 | 2004-09-09 | Hirohide Ushida | Interactive system, interaction control method, and interaction control program |
| KR20060106211A (en) * | 2005-04-06 | 2006-10-12 | 엘지전자 주식회사 | Interactive video system and its control method |
| US7958453B1 (en) * | 2006-09-29 | 2011-06-07 | Len Bou Taing | System and method for real-time, multi-user, interactive and collaborative environments on the web |
| US7970863B1 (en) * | 2003-12-29 | 2011-06-28 | AOL, Inc. | Using a home-networking gateway to manage communications |
| CN104469246A (en) * | 2013-09-13 | 2015-03-25 | 联想(北京)有限公司 | Communication service method and communication service device |
| CN104901928A (en) * | 2014-03-07 | 2015-09-09 | 中国移动通信集团浙江有限公司 | Data interaction method, device and system |
| CN106357409A (en) * | 2016-09-06 | 2017-01-25 | 中国银联股份有限公司 | Safety information interaction system and method |
| CN106888231A (en) * | 2015-12-15 | 2017-06-23 | 深圳市银信网银科技有限公司 | A kind of data interactive processing method and its device |
| CN107133297A (en) * | 2017-04-26 | 2017-09-05 | 努比亚技术有限公司 | Data interactive method, system and computer-readable recording medium |
| CA2973972A1 (en) * | 2016-09-30 | 2018-03-30 | The Toronto-Dominion Bank | System and method for generating an interaction request |
-
2018
- 2018-09-26 CN CN201811123302.2A patent/CN109582762A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1280315A1 (en) * | 1992-07-31 | 2003-01-29 | Micron Technology, Inc. | Apparatus and method for providing network security |
| JP2004172781A (en) * | 2002-11-19 | 2004-06-17 | Hitachi Ltd | Information processing apparatus for voice interaction, voice interaction processing system, and car navigation terminal |
| EP1443425A1 (en) * | 2003-01-29 | 2004-08-04 | Hewlett-Packard Company, A Delaware Corporation | Process for maintenance of a repository of documents and system for doing the same |
| US20040174981A1 (en) * | 2003-03-04 | 2004-09-09 | Hirohide Ushida | Interactive system, interaction control method, and interaction control program |
| US7970863B1 (en) * | 2003-12-29 | 2011-06-28 | AOL, Inc. | Using a home-networking gateway to manage communications |
| KR20060106211A (en) * | 2005-04-06 | 2006-10-12 | 엘지전자 주식회사 | Interactive video system and its control method |
| US7958453B1 (en) * | 2006-09-29 | 2011-06-07 | Len Bou Taing | System and method for real-time, multi-user, interactive and collaborative environments on the web |
| CN104469246A (en) * | 2013-09-13 | 2015-03-25 | 联想(北京)有限公司 | Communication service method and communication service device |
| CN104901928A (en) * | 2014-03-07 | 2015-09-09 | 中国移动通信集团浙江有限公司 | Data interaction method, device and system |
| CN106888231A (en) * | 2015-12-15 | 2017-06-23 | 深圳市银信网银科技有限公司 | A kind of data interactive processing method and its device |
| CN106357409A (en) * | 2016-09-06 | 2017-01-25 | 中国银联股份有限公司 | Safety information interaction system and method |
| CA2973972A1 (en) * | 2016-09-30 | 2018-03-30 | The Toronto-Dominion Bank | System and method for generating an interaction request |
| CN107133297A (en) * | 2017-04-26 | 2017-09-05 | 努比亚技术有限公司 | Data interactive method, system and computer-readable recording medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119293190A (en) * | 2024-11-11 | 2025-01-10 | 暗物质(北京)智能科技有限公司 | Interaction method, device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12014379B2 (en) | Automating communications using an intent classifier | |
| CN110096191B (en) | A man-machine dialogue method, device and electronic device | |
| US11790376B2 (en) | Predicting customer support requests | |
| US10949748B2 (en) | Deep learning of bots through examples and experience | |
| JP6805226B2 (en) | Service implementation based on artificial intelligence | |
| CN109514586B (en) | Method and system for realizing intelligent customer service robot | |
| CN110413758B (en) | Session framework construction method and device based on machine learning | |
| US20180090141A1 (en) | Conversational interactions using superbots | |
| EP3482359A1 (en) | Using semantic processing for customer support | |
| CN111597312A (en) | Method and device for generating multi-turn dialogue script | |
| CN111145745B (en) | Dialogue flow customization method and device | |
| CN112735407A (en) | Conversation processing method and device | |
| CN119149821B (en) | Recommendation agent system, recommendation method and recommendation device | |
| KR20240091051A (en) | Deep learning techniques for extracting embedded data from documents | |
| CN110633959A (en) | Method, device, equipment and medium for creating approval task based on graph structure | |
| CN112286485A (en) | Method and device for controlling application through voice, electronic equipment and storage medium | |
| US20240311841A1 (en) | Systems and methods for multimodal support | |
| CN105278928A (en) | IVR external interface configuration method and IVR external interface configuration device | |
| CN109582762A (en) | Data processing method and server | |
| US20160100057A1 (en) | Matching inbound call center call to commercial opportunity | |
| CN109145084B (en) | Data processing method, data processing device and server | |
| CN117610539A (en) | Intention execution method, device, electronic equipment and storage medium | |
| CN114253441B (en) | Methods and devices for enabling target functions, storage media, and electronic devices | |
| CN111610863A (en) | Information input method, device, terminal device and storage medium | |
| CN106682221B (en) | Question-answer interaction response method and device and question-answer system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201010 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: Greater Cayman, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |