CN110955769A - Processing flow construction method and electronic equipment - Google Patents

Processing flow construction method and electronic equipment Download PDF

Info

Publication number
CN110955769A
CN110955769A CN201911301153.9A CN201911301153A CN110955769A CN 110955769 A CN110955769 A CN 110955769A CN 201911301153 A CN201911301153 A CN 201911301153A CN 110955769 A CN110955769 A CN 110955769A
Authority
CN
China
Prior art keywords
processing
processing state
state
pair
target problem
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.)
Granted
Application number
CN201911301153.9A
Other languages
Chinese (zh)
Other versions
CN110955769B (en
Inventor
赵国光
闫晓芳
胡长建
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lenovo Beijing Ltd
Original Assignee
Lenovo Beijing Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lenovo Beijing Ltd filed Critical Lenovo Beijing Ltd
Priority to CN201911301153.9A priority Critical patent/CN110955769B/en
Publication of CN110955769A publication Critical patent/CN110955769A/en
Application granted granted Critical
Publication of CN110955769B publication Critical patent/CN110955769B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/03Data mining
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Debugging And Monitoring (AREA)

Abstract

The application provides a processing flow construction method and an electronic device, which can be used for constructing a processing flow aiming at a target problem based on a processing track by acquiring a dialog log aiming at the target problem, determining processing states from the dialog log, mining the processing track from the dialog log based on the processing states, and constructing the processing flow aiming at the target problem based on the processing track, wherein the processing flow is a processing flow comprising all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, the target problem can be processed through the sequential execution of the processing states in the processing flow, and the application can construct the processing flow through the acquired dialog log aiming at the target problem, so as to assist an intelligent dialog system to process the target problem, the efficiency of handling the target problem is improved.

Description

Processing flow construction method and electronic equipment
Technical Field
The invention relates to the technical field of intelligent conversation, in particular to a method for constructing a processing flow and electronic equipment.
Background
At present, a method for solving problems is provided for users, which is a large application scene of an intelligent dialogue system, the main form is that the users propose the problems, and the intelligent dialogue system processes the problems proposed by the users through multiple rounds of interaction based on a preset processing flow.
When the intelligent dialog system fails to solve the user's problem, the user typically turns to a human customer service or other system. When a human customer service or other system solves the target problem proposed by the user, different solutions are available due to different situations encountered by different users.
Therefore, how to assist the intelligent dialogue system based on the process flow of human customer service or other systems to solve the problem for the user becomes a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method for constructing a processing flow and an electronic device, so as to solve the above technical problems.
In order to achieve the purpose, the invention provides the following technical scheme:
a method of constructing a process stream, comprising:
acquiring a dialog log aiming at a target problem;
determining a processing state from the dialog log, and mining a processing track from the dialog log based on the processing state;
and constructing a processing flow aiming at the target problem based on the processing track, wherein the processing flow is a processing flow comprising all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through sequential execution of the processing states in the processing flow.
Preferably, the constructing a processing flow for the target problem based on the processing track includes:
constructing a set of processing state pairs satisfying a predetermined condition based on the processing trajectory; wherein the predetermined condition is that any processing state pair in the set of processing state pairs satisfies a causal relationship between the two processing states;
determining a maximum set of processing state pairs of the set of processing state pairs;
determining a starting processing state and an ending processing state of the processing states based on the processing trajectory;
and establishing the flow direction between the processing state pairs in the maximum processing state pair set by taking the initial processing state as the start and taking the end processing state as the end, and generating a processing flow aiming at the target problem.
Preferably, any processing state in any pair of processing states in the set of processing state pairs may include a plurality of processing states, and a selection relationship is satisfied between the plurality of processing states.
Preferably, the determining a largest processing state pair set of the processing state pair sets includes:
determining any first processing state pair and second processing state pair in the set of processing state pairs;
determining that the first processing state pair comprises the second processing state pair, reserving the first processing state pair;
reserving the second processing state pair when it is determined that the first processing state pair is included by the second processing state pair;
and when it is determined that the first processing state pair does not include the second processing state pair and is not included by the second processing state pair, retaining the first processing state pair.
Preferably, the causal relationship is used to characterize a first process state occurring first in a second process state in the dialog log, but the second process state does not occur first in the first process state;
the selection relation is used for representing that the first processing state is not a direct precedence relation of the second processing state in the dialog log, and the second processing state is not a direct precedence relation of the first processing state;
the direct precedence relationship indicates that the first processing state in the dialog log occurs first in the second processing state and is directly adjacent to the second processing state.
Preferably, the method further comprises the following steps:
generating an input-output state pair comprising an input state and an output state;
establishing a flow direction between the processing state pairs in the maximum processing state pair set by taking the starting processing state as a start and taking the ending processing state as an end to generate a processing flow for the target problem, wherein the flow direction includes:
establishing a flow direction between the input state and the initial processing state, starting with the input state;
establishing a flow direction between the output state and the end processing state, ending with the output state;
and establishing the flow direction between the processing state pairs in the maximum processing state pair set, and generating a processing flow aiming at the target problem.
Preferably, the method further comprises the following steps:
acquiring a target problem in an intelligent dialogue system; the intelligent dialogue system can complete the processing of the target problem through multiple rounds of interaction based on a preset processing flow;
processing the target problem is performed in sequence based on the processing states in the processing flow.
An electronic device, comprising:
a memory for storing a program;
the processor is used for running the program, acquiring a dialog log aiming at a target problem, determining a processing state from the dialog log, mining a processing track from the dialog log based on the processing state, and constructing a processing flow aiming at the target problem based on the processing track, wherein the processing flow is a processing flow comprising all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through the sequential execution of the processing states in the processing flow.
Preferably, the processor constructs a processing flow for the target problem based on the processing trajectory, including: constructing a processing state pair set meeting a preset condition based on the processing track, determining a maximum processing state pair set in the processing state pair set, determining a starting processing state and an ending processing state in the processing states based on the processing track, establishing a flow direction between processing state pairs in the maximum processing state pair set by taking the starting processing state as a start and the ending processing state as an end, and generating a processing flow aiming at the target problem;
wherein the predetermined condition is that a causal relationship is satisfied between any processing state pair in the set of processing state pairs.
Preferably, the determining, by the processor, a maximum processing state pair set of the processing state pair sets includes: determining any first processing state pair and second processing state pair in the processing state pair set, reserving the first processing state pair when determining that the first processing state pair contains the second processing state pair, reserving the second processing state pair when determining that the first processing state pair is contained by the second processing state pair, and reserving the first processing state pair when determining that the first processing state pair does not contain the second processing state pair and is not contained by the second processing state pair.
As can be seen from the above technical solutions, compared with the prior art, the present application provides a method for constructing a processing flow, in which a processing flow for a target problem is constructed by acquiring a dialog log for the target problem, determining a processing state from the dialog log, mining a processing trajectory from the dialog log based on the processing state, and constructing the processing flow for the target problem based on the processing trajectory, where the processing flow is a processing flow including all or part of processing states for processing the target problem, each processing state is used for characterizing one processing node of the target problem, each processing state in the processing flow is capable of generating output information based on input information related to the target problem, and the target problem can be processed by sequentially executing the processing states in the processing flow, and thus, the present application can construct a processing flow by acquiring the dialog log for the target problem, therefore, the intelligent dialogue system is assisted to process the target problem, and the efficiency of processing the target problem is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram illustrating a method for constructing a process flow according to an embodiment of the present disclosure;
FIG. 2 is a flow chart illustrating one implementation of steps for constructing a process flow for a target problem based on a process trajectory according to another method embodiment of the present application;
FIG. 3 is a flowchart illustrating another implementation of the steps for constructing a process flow for a target problem based on a process trajectory according to another embodiment of the present application;
FIG. 4 is a schematic flow chart diagram illustrating a method for constructing a process flow according to another embodiment of the present application;
FIG. 5 is a schematic illustration of a process flow of a build provided by an example of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
One embodiment of the present application provides a method for constructing a process flow, as shown in fig. 1, the method includes the following steps:
step 101: acquiring a dialog log aiming at a target problem;
the dialog log can be a dialog log of manual customer service for the target problem, and can also be a dialog log recorded in other systems except the currently applied intelligent dialog system for the target problem. Among them, the currently applied intelligent dialog system is referred to as an intelligent dialog system capable of using a subsequently constructed process flow.
The dialog log of the manual customer service records the dialog contents containing the processing state between the customer service personnel and the user for solving the target problem. The other system records the dialogue content containing the processing state between the other system and the user for solving the target problem.
Step 102: determining a processing state from the dialog log, and mining a processing track from the dialog log based on the processing state;
the processing states are used for representing processing nodes of the target problem, one processing state represents one processing node, and the processing track refers to a processing state set with the sequence of the processing states used for solving the target problem.
It should be noted that, since different solutions may be available for different users who propose the same target problem, one or more processing tracks may be mined from the dialog log for one target problem.
For example, the target issue is how to connect wifi. The dialog log includes a case 1: a dialog between the customer service and user A; case 2: a dialog between the customer service and user B; case 3: a dialog between the customer service and user C. Then based on the dialog log, the processing trajectory σ 1 ═ a, B, C, F, σ 2 ═ a, B, C, D, E, F, G, and σ 3 ═ a, B, C, D, E, F, H, G can be found. Wherein, A, B, C, D, E, F, H, G are all processing states.
Step 103: constructing a processing flow for the target problem based on the processing trajectory.
In this application, a processing flow is a processing flow including all or part of processing states for processing the target problem, each processing state is used to characterize one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed by executing the processing states in sequence in the processing flow.
Still take the target question as an example of how to connect wifi. The dialog log includes a case 1: a dialog between the customer service and user A; case 2: a dialog between the customer service and user B; case 3: a dialog between the customer service and user C. Then based on the dialog log, the processing trajectory σ 1 ═ a, B, C, F, σ 2 ═ a, B, C, D, E, F, G, and σ 3 ═ a, B, C, D, E, F, H, G can be found. Wherein, A, B, C, D, E, F, H, G are all processing states.
The constructed processing stream includes: a → B → C → D → E → F → H → G, A → B → C → D → F, A → B → C → D → E → F → G. It will be appreciated that this is merely a simple example, and that in practical applications, other processing flows not represented in the processing trajectory may be mined.
Each processing state in a processing flow is capable of generating output information based on input information associated with the target issue, the target issue being capable of being processed by sequential execution of the processing states in the processing flow. For example, in a processing flow of a → B → C → D → E → F → H → G, the target problem can be processed by the sequential execution of a → B → C → D → E → F → H → G, for example, a processing state a acquires input information "how to connect wifi" and generates output information "current state of your mobile phone? "the processing state B obtains the input information as" the mobile phone is in the on state "and generates the output information" your mobile phone model ", it should be noted that the input information may be information provided by the user or information automatically obtained by the system, for example, the input information" how to connect wifi "is input information provided by the user, and the" the mobile phone is in the on state "may be information provided by the user based on the output information" the current state of your mobile phone ", or may be automatically obtained by the system.
Therefore, in the embodiment, the processing flow can be constructed through the acquired dialog log about the target problem, so that the intelligent dialog system is assisted to process the target problem, and the efficiency of processing the target problem is improved.
Another method embodiment of the present application is directed to describing an implementation of constructing a processing flow for a target problem based on a processing trajectory. Specifically, as shown in fig. 2, the method may include the following steps:
step 201: constructing a set of processing state pairs satisfying a predetermined condition based on the processing trajectory;
wherein the predetermined condition is that a causal relationship is satisfied between any processing state pair in the set of processing state pairs. Taking the process state pair (a, B) in the set of process state pairs as an example, (a, B) needs to satisfy causal relationships.
It is noted that any processing state in any pair of processing states in the set of processing state pairs may include a plurality of processing states between which a selection relationship is satisfied. Taking the process state pair (C, (D, F)) in the process state pair set as an example, where C and D satisfy a causal relationship, C and F satisfy a causal relationship, and D and F are a plurality of process states included in the process state (D, F) in the process state pair (C, (D, F)), and D and F satisfy a selection relationship.
In this application, causal relationships are used to characterize that a first process state occurs first in a second process state in the dialog log, but the second process state does not occur first in the first process state.
And the selection relation is used for representing that in the dialog log, the first processing state is not the direct precedence relation of the second processing state, and the second processing state is not the direct precedence relation of the first processing state.
The direct precedence relationship indicates that the first processing state in the dialog log occurs first in the second processing state and is directly adjacent to the second processing state.
The causal, selection, and direct precedence relationships described above may be specifically determined based on a processing trajectory constructed by a dialog log, as the processing trajectory can be characterized as a set of processing states having a precedence order of the processing states used to solve the target problem.
The specific definition is as follows:
the direct precedence relationship a > W b is an essential condition: ヨ σ ═ t1, t2, …, tn, σ ∈ W, ti ═ a, ti +1 ═ b;
causal relationship a → sufficient condition for Wb: in W, a occurs first to b and b does not occur first to a;
select the requirement for relationship a # Wb:
Figure BDA0002321821370000071
and is
Figure BDA0002321821370000072
Wherein, W is denoted as a dialog log, a, b e T, T contains T1, T1, T2, …, tn, and is denoted as a processing state set in a processing track, and σ is denoted as a processing track.
When constructing the processing state pair set, the processing state pair set may be obtained by using the following first calculation formula.
The first calculation formula:
Figure BDA0002321821370000081
Figure BDA0002321821370000082
Figure BDA0002321821370000083
wherein, XWA is a set of process state pairs, A, B belongs to T, T is a set of process states in the process track, a1, a2 belongs to A, B1, B2 belongs to B, a → Wb is a set that a and B satisfy causal relationshipIn relation, a1# Wa2 indicates that a1 and a2 satisfy the selected relation, and b1# Wb2 indicates that b1 and b2 satisfy the selected relation.
Step 202: determining a maximum set of processing state pairs of the set of processing state pairs;
specifically, the determining a maximum processing state pair set in the processing state pair sets may include the following steps:
(1) determining any first processing state pair and second processing state pair in the set of processing state pairs;
(2) determining that the first processing state pair comprises the second processing state pair, reserving the first processing state pair;
(3) reserving the second processing state pair when it is determined that the first processing state pair is included by the second processing state pair;
(4) and when it is determined that the first processing state pair does not include the second processing state pair and is not included by the second processing state pair, retaining the first processing state pair.
Assume that the processing-state-pair set Xw { (a, B), (B, C), (C, D), (D, E), (C, F), (E, F), (F, G), (F, H), (H, G), (C, (D, F)), ((C, E), F) }
The processing state pair (a, B) is retained because it does not contain other processing state pairs and is not contained by other processing state pairs.
Since the processing state pair (C, D) is (C, (D, F), the processing state pair (C, (D, F) is retained.
Since the pair of processing states ((C, E), F) includes (E, F), the pair of processing states ((C, E), F) is retained.
In summary, the maximum processing state pair set Yw { (a, B), (B, C), (C, (D, F)), (D, E), ((C, E), F), (F, G), (F, H), (H, G) }.
When determining the maximum processing state pair set, the following second calculation formula may be specifically used.
The second calculation formula:
Figure BDA0002321821370000084
Figure BDA0002321821370000085
wherein, YWThe designation is the set of maximum processing state pairs, XWThe designation is a set of processing state pairs, A, B, A ', B' is e.g. T, T is a set of processing states in the processing trace.
Step 203: determining a starting processing state and an ending processing state of the processing states based on the processing trajectory;
in the processing track, the first one is a starting processing state, and the last one is an ending processing state. In the processing trajectory σ 1 ═ a, B, C, F, (a, B, C, D, E, F, G), and σ 3 ═ a, B, C, D, E, F, H, G, a is the start processing state and G is the end processing state.
Step 204: and establishing the flow direction between the processing state pairs in the maximum processing state pair set by taking the initial processing state as the start and taking the end processing state as the end, and generating a processing flow aiming at the target problem.
When generating the processing flow, the following third calculation formula may be used.
The third calculation formula:
FW={(a,p(A,B))|(A,B)∈YW∧a∈A}
∪{p(A,B),b}|(A,B)∈YW∧b∈B}
wherein, FWThe designation is a processing flow, A, B belongs to T, T is a processing state set in a processing track, YWThe designation is the set of maximum processing state pairs, p(A,B)Intermediate nodes for characterizing the flow direction.
Another embodiment of the method of the present application is mainly used to describe another implementation manner of constructing a processing flow for a target problem based on a processing trajectory, and specifically, as shown in fig. 3, the method may include the following steps:
step 301: constructing a set of processing state pairs satisfying a predetermined condition based on the processing trajectory;
wherein the predetermined condition is that a causal relationship is satisfied between any processing state pair in the set of processing state pairs.
Step 302: determining a maximum set of processing state pairs of the set of processing state pairs;
step 303: determining a starting processing state and an ending processing state of the processing states based on the processing trajectory;
step 304: generating an input-output state pair comprising an input state and an output state;
wherein the input state is used to characterize a start node of the process flow and the output state is used to characterize an end node of the process flow.
Specifically, the input and output state pairs may be combined into a maximum processing state pair set to generate a valid state pair set. The following fourth calculation formula can be used.
The fourth calculation formula:
pW={(p(A,B))|(A,B)∈YW}∪{iw,ow}
wherein, YWIs designated as the set of maximum processing state pairs, iWIs designated as input state, oWThe indication is an output state.
Step 305: establishing a flow direction between the input state and the initial processing state, starting with the input state;
step 306: establishing a flow direction between the output state and the end processing state, ending with the output state;
step 307: and establishing the flow direction between the processing state pairs in the maximum processing state pair set, and generating a processing flow aiming at the target problem.
When generating the processing flow, the following fifth calculation formula may be used.
The fifth calculation formula:
FW={(a,p(A,B))|(A,B)∈YW∧a∈A}
∪{p(A,B),b}|(A,B)∈YW∧b∈B}
∪{(iW,t)|t∈TI}∪{(t,ow)|t∈TO}
wherein, FWThe designation is a processing flow, A, B belongs to T, T is a processing state set in a processing track, YWThe designation is the set of maximum processing state pairs, p(A,B)Intermediate nodes for characterizing the flow direction iWIs designated as input state, oWIndication being output state, TIIndicates an initial processing state, TOThe indication is an end processing state.
Another method embodiment of the present application provides a method for constructing a process flow, as shown in fig. 4, the method includes the following steps:
step 401: acquiring a dialog log aiming at a target problem;
step 402: determining a processing state from the dialog log, and mining a processing track from the dialog log based on the processing state;
step 403: constructing a processing flow for the target problem based on the processing trajectory;
wherein the processing flow is a processing flow including all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through sequential execution of the processing states in the processing flow.
Step 404: acquiring a target problem in an intelligent dialogue system;
wherein the intelligent dialog system is capable of completing processing for the target problem through multiple rounds of interaction based on a preset processing flow.
Step 405: processing the target problem is performed in sequence based on the processing states in the processing flow.
Therefore, in the embodiment, the processing flow can be constructed through the acquired dialog log about the target problem, and the processing flow can be applied to the intelligent dialog system to process the target problem, so that the efficiency of processing the target problem is improved.
For the sake of understanding, the embodiments of the present application are briefly described as a specific example.
Assume that the data in the conversation log is as shown in table 1 below:
TABLE 1
Case column Processing state Case column Processing state Case column Processing state
Case1 A Case2 C Case2 F
Case2 A Case3 C Case3 F
Case3 A Case1 F Case2 G
Case1 B Case2 D Case3 H
Case2 B Case3 D Case3 G
Case3 B Case2 E
Case1 C Case3 E
(1) The dialog log includes 8 processing states, where a processing trace σ 1 of Case1 is (a, B, C, F), a processing trace σ 2 of Case2 is (a, B, C, D, E, F, G), and a processing trace σ 3 of Case3 is (a, B, C, D, E, F, H, G).
(2) The relationship between the pair of processing states can be found based on the processing trajectory as follows:
the direct relationship: a > WB, B > WC, C > WF, C > WD, D > WE, E > WF, F > WG, H > WG, F > WH;
cause and effect relationship: a → WB, B → WC, C → WF, C → WD, D → WE, E → WF, F → WG, H → WG, F → WH;
(3) building sets of processing state pairs
Xw={(A,B),(B,C),(C,D),(D,E),(C,F),(E,F),(F,G),(F,H),(H,G),(C,(D,F)),((C,E),F)}
Wherein, in the pair of processing states (C, (D, F)) D and F satisfy the selection relationship, and in the pair of processing states (C, E), F) C and E satisfy the selection relationship.
(4) Building a set of maximum processing state pairs
Yw={(A,B),(B,C),(C,(D,F)),(D,E),((C,E),F),(F,H),(H,G),(H,G)}
(5) Building a set of valid processing state pairs
PW={p(A,B),p(B,C),p({C},{D,F}),p(D,E),p({C,E},F),p(F,H),p(H,G),
p(H,G),P(iw,ow)}
(6) Generating a processing stream
TI=A
To=G
FW={(A,p(A,B)),(p(A,B),B),(C,p({C},{D,F})),(p({C},{D,F}),D)…(G,oW)}
A schematic diagram of a specific processing flow is shown in fig. 5, in which fig. 5 shows the processing flow a → B → C → D → E → F → H → G, a → B → C → D → F, a → B → C → D → E → F → G.
Corresponding to the above method for constructing a processing flow, the present application further provides an electronic device, and the following describes in detail several embodiments of the apparatus.
An embodiment of the present application provides an electronic device, as shown in fig. 6, the electronic device includes: memory 110 and processor 120; wherein:
the memory 110 is used to store programs;
the processor 120 is configured to run the program, execute obtaining a dialog log for a target issue, determine a processing state from the dialog log, mine a processing trace from the dialog log based on the processing state, and construct a processing flow for the target issue based on the processing trace.
The dialog log can be a dialog log of manual customer service for the target problem, and can also be a dialog log recorded in other systems except the currently applied intelligent dialog system for the target problem. Among them, the currently applied intelligent dialog system is referred to as an intelligent dialog system capable of using a subsequently constructed process flow.
The dialog log of the manual customer service records the dialog contents containing the processing state between the customer service personnel and the user for solving the target problem. The other system records the dialogue content containing the processing state between the other system and the user for solving the target problem.
The processing states are used for representing processing nodes of the target problem, one processing state represents one processing node, and the processing track refers to a processing state set with the sequence of the processing states used for solving the target problem.
It should be noted that, since different solutions may be available for different users who propose the same target problem, one or more processing tracks may be mined from the dialog log for one target problem.
In this application, a processing flow is a processing flow including all or part of processing states for processing the target problem, each processing state is used to characterize one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed by executing the processing states in sequence in the processing flow.
Therefore, in the embodiment, the processing flow can be constructed through the acquired dialog log about the target problem, so that the intelligent dialog system is assisted to process the target problem, and the efficiency of processing the target problem is improved.
Another apparatus embodiment of the present application primarily describes one implementation of a processor to construct a processing flow for a target problem based on a processing trajectory. Specifically, the processor constructs a processing flow for the target problem based on the processing trajectory, including: establishing a processing state pair set meeting a preset condition based on the processing track, determining a maximum processing state pair set in the processing state pair set, determining a starting processing state and an ending processing state in the processing states based on the processing track, establishing a flow direction between processing state pairs in the maximum processing state pair set by taking the starting processing state as a start and the ending processing state as an end, and generating a processing flow aiming at the target problem.
Wherein the predetermined condition is that a causal relationship is satisfied between any processing state pair in the set of processing state pairs.
It is noted that any processing state in any pair of processing states in the set of processing state pairs may include a plurality of processing states between which a selection relationship is satisfied.
In this application, causal relationships are used to characterize that a first process state occurs first in a second process state in the dialog log, but the second process state does not occur first in the first process state.
And the selection relation is used for representing that in the dialog log, the first processing state is not the direct precedence relation of the second processing state, and the second processing state is not the direct precedence relation of the first processing state.
The direct precedence relationship indicates that the first processing state in the dialog log occurs first in the second processing state and is directly adjacent to the second processing state.
The causal, selection, and direct precedence relationships described above may be specifically determined based on a processing trajectory constructed by a dialog log, as the processing trajectory can be characterized as a set of processing states having a precedence order of the processing states used to solve the target problem.
The specific definition is as follows:
the direct precedence relationship a > W b is an essential condition: ヨ σ ═ t1, t2, …, tn, σ ∈ W, ti ═ a, ti +1 ═ b;
causal relationship a → sufficient condition for Wb: in W, a occurs first to b and b does not occur first to a;
select the requirement for relationship a # Wb:
Figure BDA0002321821370000141
and is
Figure BDA0002321821370000142
Wherein, W is denoted as a dialog log, a, b e T, T contains T1, T1, T2, …, tn, and is denoted as a processing state set in a processing track, and σ is denoted as a processing track.
When constructing the processing state pair set, the processing state pair set may be obtained by using the following first calculation formula.
The first calculation formula:
Figure BDA0002321821370000143
Figure BDA0002321821370000144
Figure BDA0002321821370000145
wherein, XWThe method comprises the steps of representing a set of processing state pairs, wherein A, B belongs to T, T represents a set of processing states in a processing track, a1, a2 belongs to A, B1, B2 belongs to B, a → Wb represents that a and B satisfy causal relationship, a1# Wa2 represents that a1 and a2 satisfy selection relationship, and B1# Wb2 represents that B1 and B2 satisfy selection relationship.
In this application, the determining, by the processor, a largest processing state pair set of the processing state pair sets may include: determining any first processing state pair and second processing state pair in the processing state pair set, reserving the first processing state pair when determining that the first processing state pair contains the second processing state pair, reserving the second processing state pair when determining that the first processing state pair is contained by the second processing state pair, and reserving the first processing state pair when determining that the first processing state pair does not contain the second processing state pair and is not contained by the second processing state pair.
When determining the maximum processing state pair set, the following second calculation formula may be specifically used.
The second calculation formula:
Figure BDA0002321821370000146
Figure BDA0002321821370000147
wherein, YWThe designation is the set of maximum processing state pairs, XWThe designation is a set of processing state pairs, A, B, A ', B' is e.g. T, T is a set of processing states in the processing trace.
When generating the processing flow, the following third calculation formula may be used.
The third calculation formula:
FW={(a,p(A,B))|(A,B)∈YW∧a∈A}
∪{p(A,B),b}|(A,B)∈YW∧b∈B}
wherein, FWThe designation is a processing flow, A, B belongs to T, T is a processing state set in a processing track, YWThe designation is the set of maximum processing state pairs, p(A,B)Intermediate nodes for characterizing the flow direction.
Another embodiment of the apparatus in this application is mainly used to describe another implementation manner of constructing, by a processor, a processing flow for a target problem based on a processing trajectory, and specifically, the constructing, by the processor, the processing flow for the target problem based on the processing trajectory includes: establishing a processing state pair set meeting a preset condition based on the processing track, determining a maximum processing state pair set in the processing state pair set, determining a starting processing state and an ending processing state in the processing states based on the processing track, generating an input-output state pair, wherein the input-output state pair comprises an input state and an output state, establishing a flow direction between the input state and the starting processing state, establishing a flow direction between the output state and the ending processing state by taking the input state as a start, establishing a flow direction between the processing state pairs in the maximum processing state pair set by taking the output state as an end, and generating a processing flow for the target problem.
Wherein the input state is used to characterize a start node of the process flow and the output state is used to characterize an end node of the process flow.
Specifically, the input and output state pairs may be combined into a maximum processing state pair set to generate a valid state pair set. The following fourth calculation formula can be used.
The fourth calculation formula:
pW={(p(A,B))|(A,B)∈YW}∪{iw,ow}
wherein, YWIs designated as the set of maximum processing state pairs, iWIs designated as input state, oWThe indication is an output state.
When generating the processing flow, the following fifth calculation formula may be used.
The fifth calculation formula:
FW={(a,p(A,B))|(A,B)∈YW∧a∈A}
∪{p(A,B),b}|(A,B)∈YW∧b∈B}
∪{(iW,t)|t∈TI}∪{(t,ow)|t∈TO}
wherein, FWThe designation is a processing flow, A, B belongs to T, T is a processing state set in a processing track, YWThe designation is the set of maximum processing state pairs, p(A,B)Intermediate for characterizing flow directionNode, iWIs designated as input state, oWIndication being output state, TIIndicates an initial processing state, TOThe indication is an end processing state.
Yet another apparatus embodiment of the present application provides an electronic device comprising a memory and a processor; wherein:
the memory is used for storing programs;
the processor is used for acquiring a dialog log aiming at a target problem, determining a processing state from the dialog log, mining a processing track from the dialog log based on the processing state, constructing a processing flow aiming at the target problem based on the processing track, acquiring the target problem in the intelligent dialog system, and sequentially executing processing of the target problem based on the processing state in the processing flow.
Wherein the processing flow is a processing flow including all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through sequential execution of the processing states in the processing flow.
The intelligent dialogue system can complete the processing aiming at the target problem through multiple rounds of interaction based on the preset processing flow.
Therefore, in the embodiment, the processing flow can be constructed through the acquired dialog log about the target problem, and the processing flow can be applied to the intelligent dialog system to assist the intelligent dialog system in processing the target problem, so that the efficiency of processing the target problem is improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method of constructing a process stream, comprising:
acquiring a dialog log aiming at a target problem;
determining a processing state from the dialog log, and mining a processing track from the dialog log based on the processing state;
and constructing a processing flow aiming at the target problem based on the processing track, wherein the processing flow is a processing flow comprising all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through sequential execution of the processing states in the processing flow.
2. The method of claim 1, the constructing a processing flow for the target issue based on the processing trajectory, comprising:
constructing a set of processing state pairs satisfying a predetermined condition based on the processing trajectory; wherein the predetermined condition is that any processing state pair in the set of processing state pairs satisfies a causal relationship between the two processing states;
determining a maximum set of processing state pairs of the set of processing state pairs;
determining a starting processing state and an ending processing state of the processing states based on the processing trajectory;
and establishing the flow direction between the processing state pairs in the maximum processing state pair set by taking the initial processing state as the start and taking the end processing state as the end, and generating a processing flow aiming at the target problem.
3. The method of claim 2, any processing state of any pair of processing states of the set of processing state pairs may comprise a plurality of processing states between which a selection relationship is satisfied.
4. The method of claim 2 or 3, the determining a largest set of processing state pairs of the set of processing state pairs, comprising:
determining any first processing state pair and second processing state pair in the set of processing state pairs;
determining that the first processing state pair comprises the second processing state pair, reserving the first processing state pair;
reserving the second processing state pair when it is determined that the first processing state pair is included by the second processing state pair;
and when it is determined that the first processing state pair does not include the second processing state pair and is not included by the second processing state pair, retaining the first processing state pair.
5. The method of claim 2 or 3, the causal relationship to characterize a first process state occurring first to a second process state in the dialog log, but the second process state not occurring first to the first process state;
the selection relation is used for representing that the first processing state is not a direct precedence relation of the second processing state in the dialog log, and the second processing state is not a direct precedence relation of the first processing state;
the direct precedence relationship indicates that the first processing state in the dialog log occurs first in the second processing state and is directly adjacent to the second processing state.
6. The method of claim 5, further comprising:
generating an input-output state pair comprising an input state and an output state;
establishing a flow direction between the processing state pairs in the maximum processing state pair set by taking the starting processing state as a start and taking the ending processing state as an end to generate a processing flow for the target problem, wherein the flow direction includes:
establishing a flow direction between the input state and the initial processing state, starting with the input state;
establishing a flow direction between the output state and the end processing state, ending with the output state;
and establishing the flow direction between the processing state pairs in the maximum processing state pair set, and generating a processing flow aiming at the target problem.
7. The method of claim 1, further comprising:
acquiring a target problem in an intelligent dialogue system; the intelligent dialogue system can complete the processing of the target problem through multiple rounds of interaction based on a preset processing flow;
processing the target problem is performed in sequence based on the processing states in the processing flow.
8. An electronic device, comprising:
a memory for storing a program;
the processor is used for running the program, acquiring a dialog log aiming at a target problem, determining a processing state from the dialog log, mining a processing track from the dialog log based on the processing state, and constructing a processing flow aiming at the target problem based on the processing track, wherein the processing flow is a processing flow comprising all or part of processing states for processing the target problem, each processing state is used for representing one processing node of the target problem, each processing state in the processing flow can generate output information based on input information related to the target problem, and the target problem can be processed through the sequential execution of the processing states in the processing flow.
9. The electronic device of claim 8, the processor building a processing flow for the target issue based on the processing trajectory, comprising: constructing a processing state pair set meeting a preset condition based on the processing track, determining a maximum processing state pair set in the processing state pair set, determining a starting processing state and an ending processing state in the processing states based on the processing track, establishing a flow direction between processing state pairs in the maximum processing state pair set by taking the starting processing state as a start and the ending processing state as an end, and generating a processing flow aiming at the target problem;
wherein the predetermined condition is that a causal relationship is satisfied between any processing state pair in the set of processing state pairs.
10. The electronic device of claim 9, the processor to determine a largest set of processing state pairs of the set of processing state pairs, comprising: determining any first processing state pair and second processing state pair in the processing state pair set, reserving the first processing state pair when determining that the first processing state pair contains the second processing state pair, reserving the second processing state pair when determining that the first processing state pair is contained by the second processing state pair, and reserving the first processing state pair when determining that the first processing state pair does not contain the second processing state pair and is not contained by the second processing state pair.
CN201911301153.9A 2019-12-17 2019-12-17 Method for constructing processing stream and electronic equipment Active CN110955769B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911301153.9A CN110955769B (en) 2019-12-17 2019-12-17 Method for constructing processing stream and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911301153.9A CN110955769B (en) 2019-12-17 2019-12-17 Method for constructing processing stream and electronic equipment

Publications (2)

Publication Number Publication Date
CN110955769A true CN110955769A (en) 2020-04-03
CN110955769B CN110955769B (en) 2023-07-21

Family

ID=69982083

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911301153.9A Active CN110955769B (en) 2019-12-17 2019-12-17 Method for constructing processing stream and electronic equipment

Country Status (1)

Country Link
CN (1) CN110955769B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150193429A1 (en) * 2014-01-09 2015-07-09 International Business Machines Corporation Automatic Generation of Question-Answer Pairs from Conversational Text
CN106095965A (en) * 2016-06-17 2016-11-09 上海智臻智能网络科技股份有限公司 A kind of data processing method and device
US20170169115A1 (en) * 2015-12-09 2017-06-15 Industrial Technology Research Institute Internet question answering system and method, and computer readable recording media
CN108804643A (en) * 2018-06-05 2018-11-13 北京玄科技有限公司 Flow dispensing unit, method and the intelligent robot interactive system of more wheel sessions
CN109189803A (en) * 2018-09-03 2019-01-11 深圳前海微众银行股份有限公司 Question and answer are to construction method, device and computer readable storage medium
CN109308320A (en) * 2018-07-20 2019-02-05 北京智能点科技有限公司 Conversation process configuration method is taken turns more by a kind of robot
CN109344242A (en) * 2018-09-28 2019-02-15 广东工业大学 A kind of dialogue answering method, device, equipment and storage medium
CN109783510A (en) * 2019-01-22 2019-05-21 深圳追一科技有限公司 Customer service auxiliary robot, method and system
US20190188585A1 (en) * 2017-12-15 2019-06-20 Shanghai Xiaoi Robot Technology Co., Ltd. Multi-round questioning and answering methods, methods for generating a multi-round questioning and answering system, and methods for modifying the system
CN110020014A (en) * 2017-12-15 2019-07-16 上海智臻智能网络科技股份有限公司 More wheel question and answer systems
CN110019149A (en) * 2019-01-30 2019-07-16 阿里巴巴集团控股有限公司 A kind of method for building up of service knowledge base, device and equipment

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150193429A1 (en) * 2014-01-09 2015-07-09 International Business Machines Corporation Automatic Generation of Question-Answer Pairs from Conversational Text
US20170169115A1 (en) * 2015-12-09 2017-06-15 Industrial Technology Research Institute Internet question answering system and method, and computer readable recording media
CN106095965A (en) * 2016-06-17 2016-11-09 上海智臻智能网络科技股份有限公司 A kind of data processing method and device
US20190188585A1 (en) * 2017-12-15 2019-06-20 Shanghai Xiaoi Robot Technology Co., Ltd. Multi-round questioning and answering methods, methods for generating a multi-round questioning and answering system, and methods for modifying the system
CN110020014A (en) * 2017-12-15 2019-07-16 上海智臻智能网络科技股份有限公司 More wheel question and answer systems
CN108804643A (en) * 2018-06-05 2018-11-13 北京玄科技有限公司 Flow dispensing unit, method and the intelligent robot interactive system of more wheel sessions
CN109308320A (en) * 2018-07-20 2019-02-05 北京智能点科技有限公司 Conversation process configuration method is taken turns more by a kind of robot
CN109189803A (en) * 2018-09-03 2019-01-11 深圳前海微众银行股份有限公司 Question and answer are to construction method, device and computer readable storage medium
CN109344242A (en) * 2018-09-28 2019-02-15 广东工业大学 A kind of dialogue answering method, device, equipment and storage medium
CN109783510A (en) * 2019-01-22 2019-05-21 深圳追一科技有限公司 Customer service auxiliary robot, method and system
CN110019149A (en) * 2019-01-30 2019-07-16 阿里巴巴集团控股有限公司 A kind of method for building up of service knowledge base, device and equipment

Also Published As

Publication number Publication date
CN110955769B (en) 2023-07-21

Similar Documents

Publication Publication Date Title
CN108961052A (en) Verification method, storage method, device, equipment and the medium of block chain data
CN106503242B (en) A kind of intelligent interactive method, device and server
US20220253710A1 (en) Human-Machine Multi-Turn Conversation Method and System for Human-Machine Interaction, and Intelligent Apparatus
CN111385639B (en) Video special effect adding method, device, equipment and storage medium
JP6167187B2 (en) Query generation method and query generation apparatus
CN104484038B (en) The control method and device of smart machine
CN106294564A (en) A kind of video recommendation method and device
CN106911963A (en) Method for information display and device in a kind of terminal device
CN109582289A (en) The processing method of regular flow, system, storage medium and processor in regulation engine
CN110717647A (en) Decision flow construction method and device, computer equipment and storage medium
CN111581390A (en) Knowledge graph construction method and device and electronic equipment
CN113573093A (en) Live broadcast data analysis method and device, electronic equipment and storage medium
CN106845625A (en) A kind of interactive output intent and robot for robot
CN110932929B (en) Method, system and medium for classifying and extracting satellite telemetry packets in CCSDS system
CN111062612B (en) Construction method of auxiliary processing stream and electronic equipment
CN110955769B (en) Method for constructing processing stream and electronic equipment
US10721281B2 (en) Method, system and non-transitory computer-readable recording medium for providing a multilateral communication service
CN112560939B (en) Model verification method and device and computer equipment
US10659304B2 (en) Method of allocating processes on node devices, apparatus, and storage medium
JP5394599B1 (en) Information providing apparatus, information providing method, and information providing program
CN110909072B (en) Data table establishment method, device and equipment
US10489429B2 (en) Relationship graph evaluation system
CN105704173B (en) A kind of cluster system data location mode and server
WO2023142349A1 (en) Behavior sequence generation method and apparatus, storage medium and electronic device
CN106131134A (en) A kind of message content merges De-weight method and 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
GR01 Patent grant
GR01 Patent grant