CN113158692B - Semantic recognition-based multi-intention processing method, system, equipment and storage medium - Google Patents
Semantic recognition-based multi-intention processing method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN113158692B CN113158692B CN202110435537.0A CN202110435537A CN113158692B CN 113158692 B CN113158692 B CN 113158692B CN 202110435537 A CN202110435537 A CN 202110435537A CN 113158692 B CN113158692 B CN 113158692B
- Authority
- CN
- China
- Prior art keywords
- intention
- type
- target
- operation flow
- intents
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The invention relates to the field of voice recognition, and provides a multi-intention processing method based on semantic recognition, which comprises the following steps: receiving voice to be recognized, and performing transcription operation on the voice to be recognized to obtain text to be recognized; splitting the text to be identified into a plurality of target texts; identifying target intentions corresponding to each target text through a pre-trained semantic identification model so as to obtain a plurality of target intentions; obtaining the intention type of each target intention, and determining a target operation strategy according to the intention type of each target intention; and determining one or more operational flows based on the target operational policy to perform a responsive operation based on the one or more operational flows. The invention improves the efficiency, accuracy and voice interaction efficiency of the intention recognition, so that the voice reply system is more anthropomorphic, and the user experience is improved.
Description
Technical Field
The embodiment of the invention relates to the field of voice recognition, in particular to a multi-intention processing method, a system, equipment and a storage medium based on semantic recognition.
Background
At present, the intention recognition has a plurality of difficulties, firstly, a voice recognition system is difficult to accurately recognize the intention of a user; second, if there are multiple meanings in a sentence of a user, the speech recognition system cannot process well, or the processing is not the core meaning of the user; third, the problem is not completely handled, and a plurality of meanings of the user cannot be comprehensively handled. Based on the above points, in the voice interaction of the existing voice recognition system, the problems of incapacity of questions, light weight avoidance, incapability of processing core meanings of users and the like often occur, or the problems that only one intention is replied when a plurality of intentions occur, and the comprehensive processing is impossible often occur. Therefore, how to improve accuracy of intention recognition, thereby improving voice interaction efficiency, becomes a technical problem to be solved currently.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a semantic recognition-based multi-intent processing method, system, device and readable storage medium, so as to solve the problems of low accuracy of intent recognition and low efficiency of voice interaction.
In order to achieve the above object, an embodiment of the present invention provides a multi-intent processing method based on semantic recognition, where the steps of the method include:
Receiving voice to be recognized, and performing transcription operation on the voice to be recognized to obtain text to be recognized;
splitting the text to be identified into a plurality of target texts;
identifying target intentions corresponding to each target text through a pre-trained semantic identification model so as to obtain a plurality of target intentions;
obtaining the intention type of each target intention, and determining a target operation strategy according to the intention type of each target intention; a kind of electronic device with high-pressure air-conditioning system
One or more operational flows are determined based on the target operational policy to perform responsive operations based on the one or more operational flows.
For example, the intention type includes at least one of an ending type intention, a trunk type intention, and an objection type intention, wherein the objection type intention includes at least one of a resolvable type intention, an unresolved type intention, and an unsolved type intention;
the step of determining a target operation strategy according to the intention type of each target intention comprises the following steps:
determining the target operation strategy according to the intention type of each target intention and the preconfigured operation priority;
the operation priority is an execution sequence corresponding to the operation flow of each target intention, and the execution sequence of each operation flow is as follows: an operation flow of ending type intention, an operation flow of failing to solve type intention, an operation flow of backbone type intention, an operation flow of resolvable type intention, and an operation flow of not having to solve type intention.
Illustratively, the step of determining the target operation policy according to the intention type of each target intention includes:
when the ending type intents exist in the intention types of the respective target intents, determining an operation flow for executing the ending type intents as the target operation policy.
Illustratively, the step of determining the target operation policy according to the intention type of each target intention includes:
when the ending type intention does not exist in the intention types of the target intents, judging whether the objection type intention exists or not;
if the objection type intention exists, detecting whether the objection type intention comprises the resolvable type intention;
if the objection type intention comprises the resolvable intention, preferentially executing the operation flow of the resolvable intention, and then executing the operation flow of the unresolved intention, the operation flow of the trunk type intention and the operation flow of the unresolved intention according to the operation priority, wherein the operation flow with the highest current operation priority is determined to be the target operation strategy; a kind of electronic device with high-pressure air-conditioning system
And if the objection type intention does not comprise the resolvable type intention, determining an operation flow with highest current operation priority among the operation flow executing the unresolved type intention, the operation flow with the main type intention and the operation flow without the resolvable type intention according to the operation priority as the target operation policy.
Exemplary, the step of executing the operation flow with the unresolved intent, the operation flow with the backbone type intent, and the operation flow with the unresolved intent according to the operation priority, where the operation flow with the highest current operation priority includes:
when the operation flow with the highest current operation priority is the operation flow of the unresolved type intention and the plurality of target intents comprise a plurality of unresolved type intents arranged according to a preset sequence, executing the operation flow of the last unresolved type intention in the plurality of unresolved type intents, wherein the preset sequence comprises the position sequence of the target text corresponding to each unresolved type intention in the text to be identified;
when the operation flow with the highest current operation priority is the operation flow of the main type intention, and the plurality of target intents comprise a plurality of main type intents arranged according to the preset sequence, executing the operation flow of the last main type intention in the plurality of main type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each main type intention in the text to be identified; a kind of electronic device with high-pressure air-conditioning system
When the operation flow with the highest current operation priority is the operation flow of the unsolved type intention, and the plurality of target intents comprise a plurality of unsolved type intents arranged according to the preset sequence, executing the operation flow of the last unsolved type intention in the plurality of unsolved type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each unsolved type intention in the text to be identified.
The response operation includes a play operation and a follow-up operation, wherein each operation flow of the intention type corresponds to one play operation, and each play operation corresponds to one follow-up operation;
the step of determining one or more operation flows based on the target operation policy to perform a responsive operation based on the one or more operation flows includes:
executing corresponding playing operation according to each operation flow; a kind of electronic device with high-pressure air-conditioning system
And determining and executing a follow-up operation corresponding to the last play operation according to the last play operation in the play operations.
Exemplary, further comprising: uploading the target operating policy to a blockchain.
To achieve the above object, an embodiment of the present invention further provides a multi-intent processing system based on semantic recognition, including:
The receiving module is used for receiving the voice to be recognized and performing transcription operation on the voice to be recognized to obtain a text to be recognized;
the splitting module is used for splitting the text to be identified into a plurality of target texts;
the recognition module is used for recognizing the target intention corresponding to each target text through a pre-trained semantic recognition model so as to obtain a plurality of target intentions;
the determining module is used for obtaining the intention type of each target intention and determining a target operation strategy according to the intention type of each target intention; a kind of electronic device with high-pressure air-conditioning system
And the execution module is used for determining one or more operation flows based on the target operation strategy so as to execute response operation based on the one or more operation flows.
To achieve the above object, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the computer program implements the steps of the semantic recognition based multi-purpose processing method as described above when executed by the processor.
To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium having stored therein a computer program executable by at least one processor to cause the at least one processor to perform the steps of the semantic recognition based multi-purpose processing method as described above.
According to the multi-intention processing method, the system, the computer equipment and the computer readable storage medium based on semantic recognition, provided by the embodiment of the invention, through carrying out sentence breaking on the text to be recognized and carrying out intention recognition on a plurality of target phrases after sentence breaking, the problem that intention recognition is difficult due to more Chinese in the text to be recognized or intention such as cross, contradiction and inversion in the text to be recognized is solved, the accuracy of recognizing the intention of the text to be recognized is improved, the difficulty of recognizing the intention of the text to be recognized is reduced, and the intention recognition efficiency is improved; the target operation strategies are configured according to the intention types of the target intentions, and the operation flows for executing the intention operations of the targets are adjusted according to the target operation strategies, so that different operation flows for executing different replies according to different graphs, for example, the operation flows for executing key replies according to important intention types, the operation flows for executing selective replies according to secondary intention types and the operation flows for executing non-replies according to non-important intention types can be executed, so that replies to some voice intentions are reduced, the efficiency of voice interaction is improved, a voice reply system is more personified, and the user experience is improved.
Drawings
FIG. 1 is a flow chart of a multi-intent processing method based on semantic recognition according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a program module of a second embodiment of a semantic recognition-based multi-purpose processing system according to the present invention;
fig. 3 is a schematic diagram of a hardware structure of a third embodiment of the computer device of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
Example 1
Referring to FIG. 1, a flowchart of steps of a semantic recognition based multi-intent processing method is shown in an embodiment of the present invention. It will be appreciated that the flow charts in the method embodiments are not intended to limit the order in which the steps are performed. The semantic recognition-based multi-purpose processing system in the present embodiment may be executed in the computer device 2, and an exemplary description will be made below with the computer device 2 as an execution subject. Specifically, the following is described.
Step S100, receiving voice to be recognized, and performing transcription operation on the voice to be recognized to obtain text to be recognized.
The computer device 2 may receive the speech to be recognized and perform a transcription operation on the speech to be recognized to obtain the text to be recognized. The voice to be recognized may also be obtained by the computer device 2 in real time; as in the case of intelligent customer service, the computer device 2 may acquire in real time the call voice of a service object (target customer) served by the intelligent customer service. The voice to be recognized may be an nth voice of the target client, and the voice to be recognized may also be a voice segment.
For example, the computer device 2 may perform a transcription operation on the speech to be recognized to obtain a plurality of speech texts; then calculating the matching degree between each voice text and the voice to be recognized; and taking the voice text with the highest matching degree with the voice to be recognized in the voice texts as the text to be recognized. Wherein the computer device 2 calculates the matching degree between each voice text w and the voice to be recognized, and specifically can take the voice text with the highest matching degree with the voice to be recognized as the text to be recognized
The p (w|x) can be converted into p (x|w) p (w) through Bayesian formula for calculationWherein p (x|w) represents an acoustic model; p (w) represents a language model; p (x) represents the acoustic feature probability, which is constant for different w, calculated +.>And can be ignored. According to the method, the device and the system, the text to be recognized with the highest matching degree with the voice to be recognized is obtained from the plurality of voice texts, so that the transcription accuracy of voice recognition is improved.
And step S102, splitting the text to be recognized into a plurality of target texts.
After obtaining the text to be recognized, the computer device 2 may perform a sentence breaking operation on the text to be recognized to obtain the multiple target texts.
Step S104, identifying target intentions corresponding to each target text through a pre-trained semantic identification model so as to obtain a plurality of target intentions.
After obtaining the plurality of target texts, the computer device 2 may input the plurality of target texts into the semantic recognition model, so as to perform semantic recognition on each target text through the semantic recognition model, and output a plurality of target intents corresponding to the plurality of target texts. The semantic recognition model may be a trained NLP (intent recognition: natural Language Processing) recognition model, among others.
Step S106, obtaining the intention type of each target intention, and determining a target operation strategy according to the intention type of each target intention.
The intent types of the plurality of target intents include at least one of an ending type intent, a backbone type intent, and an objection type intent, wherein the objection type intent includes at least one of a resolvable type intent, an unresolved type intent, and an unsolved type intent. Wherein:
the ending intention is: the intention corresponding to the voice of the call ending language exists;
the backbone is intended to be: intent corresponding to a main topic corresponding to the whole text to be identified;
the resolvable intent is: similar to query-like intents, which in most cases can be replied to with a fixed solution voice;
the unsolvable intent is: intent corresponding to the problem of difficulty, intent which cannot be solved at present;
the purpose of the unsolved solution is: similar to the intent corresponding to the consonant-type speech, there is not much actual meaning or result-like intent belonging to causal relationships.
For example, the computer device 2 may determine the intent type for each target intent based on the respective target intent carrying tags. In this embodiment, when identifying the target intention corresponding to the target text, the semantic identification model may further determine an intention type of the intention, and configure a corresponding intention label for each target intention according to the intention type of each target intention, where one intention type corresponds to one intention label.
In an exemplary embodiment, the step S106 may further include: determining the target operation strategy according to the intention type of each target intention and the preconfigured operation priority; the operation priority is an execution sequence corresponding to the operation flow of each target intention, and the execution sequence of each operation flow is as follows: an operation flow of ending type intention, an operation flow of failing to solve type intention, an operation flow of backbone type intention, an operation flow of resolvable type intention, and an operation flow of not having to solve type intention. According to the voice system and the voice processing method, voice intentions are classified, different priorities are configured for different voice types, so that intentions with high priorities in a plurality of target intentions can be recovered preferentially, and the intelligent recovery efficiency of the voice system is improved.
In an exemplary embodiment, the step S106 may further include: when the ending type intents exist in the intention types of the respective target intents, determining an operation flow for executing the ending type intents as the target operation policy. The operation flow of the ending intention is an ending call flow, specifically, when one of the voice intentions in the text to be recognized is the ending intention, for example, in a scene of intelligent customer service, the ending intention is the intention of the target user to end the call, if the text to be recognized has words such as "i hang", "i hang first", "bye", etc., then the text to be recognized has the ending intention, that is, the target user cannot keep on talking at present. At this time, the computer device 2 may execute the ending call flow; wherein, when the target user does not hang up immediately, the preconfigured reply voice (speaking) is played.
In an exemplary embodiment, the step S106 may further include steps S200 to S204, wherein: step S200 of judging whether or not the objection type intention exists when the ending type intention does not exist in the intention type of each of the target intents; if the objection type intention exists, detecting whether the objection type intention comprises the resolvable type intention; step S202, if the objection type intention includes the resolvable intention, preferentially executing the operation flow of the resolvable intention, and then determining the operation flow with highest current operation priority among the operation flow of the unresolved intention, the operation flow of the trunk type intention and the operation flow without the resolvable intention as the target operation strategy according to the operation priorities; and step S204, if the objection type intention does not include the resolvable intention, determining an operation flow with highest current operation priority among the operation flow with the unresolved intention, the operation flow with the trunk type intention and the operation flow without the resolvable intention as the target operation policy.
For example, the computer device 2 may pre-configure a voice response library, wherein the voice response library includes a plurality of answer-type voices and a plurality of answer-type voices. The plurality of answer-type voices are used for replying to the resolvable intent, and the plurality of answer-type voices are used for replying to voice intent which cannot be answered by each answer-type voice.
When detecting that the objection type intention includes the resolvable type intention, the operation flow of the resolvable type intention is as follows: the computer device 2 first matches one or more answer-type voices corresponding to the resolvable type intention from the plurality of answer-type voices, then matches a reply-type voice corresponding to the voice intention of the current operation priority from the plurality of return-type voices according to the operation priority, and preferentially plays the one or more answer-type voices, and then plays the reply-type voice corresponding to the voice intention of the current operation priority. Wherein, the voice intention of the current operation priority may be one of an unresolved intention, a stem intention, a resolvable intention, and an unresolved intention. The voice text corresponding to the resolvable type intention generally appears in the form of question sentences, and the question sentences are problems which are solved in advance. E.g. who you are (corresponding intention: ask identity), what you call for me to do (corresponding intention: ask incoming call purpose).
When detecting that the objection type intention does not include the resolvable type intention, the current operation flow is: the computer device 2 matches, from the plurality of reply-type voices, reply-type voices corresponding to the voice intention of the current operation priority according to the operation priority, and plays the reply-type voices corresponding to the voice intention of the current operation priority.
In an exemplary embodiment, the step S204 may further include steps S300 to S304, where: step S300, when the operation flow with the highest current operation priority is the operation flow of the unresolved type intention, and the multiple target intents comprise multiple unresolved type intents arranged according to a preset sequence, executing the operation flow of the last unresolved type intention in the multiple unresolved type intents, wherein the preset sequence comprises the position sequence of the target text corresponding to each unresolved type intention in the text to be identified; step S302, when the operation flow with the highest current operation priority is the operation flow of the main type intention, and the plurality of target intents include a plurality of main type intents arranged according to the preset sequence, executing the operation flow of the last main type intention of the plurality of main type intents, where the preset sequence further includes a position sequence of a target text corresponding to each main type intention in the text to be identified; and step S304, when the operation flow with the highest current operation priority is the operation flow with the non-resolution type intents, and the plurality of target intents comprise a plurality of non-resolution type intents arranged according to the preset sequence, executing the operation flow with the last non-resolution type intention in the plurality of non-resolution type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each non-resolution type intention in the text to be identified. The embodiment improves the voice reply efficiency by executing the operation flow of the last intention in the plurality of the same type intentions.
Step S108, determining one or more operation flows based on the target operation policy, so as to execute a response operation based on the one or more operation flows.
In an exemplary embodiment, the response operation includes a play operation and a follow-up operation, wherein each operation flow of the intention type corresponds to one play operation, and each play operation corresponds to one follow-up operation; the step S108 may further include steps S400 to S402, where: step S400, executing corresponding playing operation according to each operation flow; and step S402, determining and executing a subsequent operation corresponding to the last playing operation according to the last playing operation in the playing operations. The embodiment improves the voice reply efficiency by executing the operation flow of the last intention in the plurality of the same type intentions.
According to the method, the long sentence (text to be recognized) is subjected to sentence breaking, and the intent recognition is carried out on a plurality of target short sentences after sentence breaking, wherein the problems that the long sentence intent library is difficult to maintain or the intent recognition is easy to disorder due to the fact that the long sentence has many characters and is difficult to recognize or the long sentence has the intentions such as cross, contradiction and reverse rotation are avoided by carrying out the intent recognition on the short sentences after sentence breaking; the intention recognition efficiency and accuracy are improved. In this embodiment, the operation priority corresponding to each target intention may be further used to adjust the operation flow of each target intention (for example, the answer type voice or the reply type voice is used to implement targeted reply and/or diversity reply to various types of intentions, and meanwhile, the operation priority configuration is used to implement diversity control to the operation flow), so that the voice reply system is more anthropomorphic, thereby improving the user experience of the target user.
In order to make the present embodiment clearer, the present embodiment further provides a specific example table of the target operation policy, as shown in table 1:
TABLE 1
In table 1, the "ending" is that one or more ending type intents are included in the target intents corresponding to the text to be recognized; the trunk comprises one or more trunk-type intents in a plurality of target intents corresponding to the text to be identified; "objection" is that one or more objections type intents are included in the multiple target intents corresponding to the text to be identified; "none" is that one or more unresolved intents are included in the target intents corresponding to the text to be identified; "resolvable" is that one or more resolvable intents are included in a plurality of target intents corresponding to the text to be recognized; and the 'none' comprises one or more unsolved intents in a plurality of target intents corresponding to the text to be identified.
In the play operation of table 1, play one is: sequentially playing answer type voices corresponding to the resolvable type intention; and playing the second step: broadcasting the last reply voice corresponding to the unresolved type intention; and playing three steps: the last reply voice corresponding to the unsolved intention is broadcast; and playing four steps: broadcasting the reply type voice corresponding to the last trunk type intention; the fifth playing step is as follows: and broadcasting the reply type voice corresponding to the ending type intention and ending the call.
In the subsequent operations of table 1, operation one is: playing a corresponding subsequent operation; the second operation is as follows: playing the corresponding subsequent operation; the third operation is as follows: playing the corresponding follow-up operation; the operation four is as follows: and playing the corresponding follow-up operation.
For ease of understanding, this embodiment also provides a specific example:
the text to be recognized: "you are who you call to find me dry what me is now at a meeting where it is inconvenient to speak".
A plurality of target texts corresponding to the text to be identified: you are/you make a call to find me dry what i am now in a meeting/here are inconvenient to speak (to/make a sentence break).
Intent corresponding to each target text: you are who-ask identity/you call what you do to find me-ask incoming call destination/me is now in a meeting-in a meeting/here it is inconvenient to speak-there is no time.
Resolvable intent: challenge identity/challenge incoming call destination.
The unsolvable intention is: at the meeting.
Without solving the intention: there is no time.
The method solves the problems that: i am XX, the call coming from because of XXXX things, i am late to contact you can if you are now in a meeting.
The target operation strategy corresponding to the text to be identified is as follows: the computer device 2 matches the two answer voices corresponding to the "inquiry identity" and the "inquiry incoming call destination" from the plurality of answer voices, then matches the reply voice corresponding to the "meeting" from the plurality of answer voices, and plays the two answer voices corresponding to the "inquiry identity" and the "inquiry incoming call destination" and the reply voice corresponding to the "meeting".
The voice played by the playing operation is as follows: i am XX, the call coming from because of XXXX things, i am late to contact you can if you are now in a meeting.
The following operations: waiting for the target user to reply again.
Illustratively, the semantic recognition-based multi-intention processing method further comprises: uploading the target operating policy to a blockchain.
Illustratively, uploading the target operating policy to the blockchain may ensure its security and fair transparency. The blockchain referred to in this example is a novel mode of application for computer technology such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Example two
FIG. 2 is a schematic diagram of a program module of a second embodiment of a semantic recognition-based multi-purpose processing system according to the present invention. The semantic recognition based multi-intent processing system 20 may include or be partitioned into one or more program modules stored in a storage medium and executed by one or more processors to perform the present invention and implement the semantic recognition based multi-intent processing method described above. Program modules depicted in the embodiments of the present invention are directed to a series of computer program instruction segments capable of performing particular functions, which are more suitable than the program itself to describe the execution of the semantic recognition based multi-purpose processing system 20 in a storage medium. The following description will specifically describe functions of each program module of the present embodiment:
The receiving module 200 receives the voice to be recognized, and performs a transcription operation on the voice to be recognized to obtain a text to be recognized.
The splitting module 202 is configured to split the text to be identified into a plurality of target texts.
The recognition module 204 is configured to recognize, through a pre-trained semantic recognition model, a target intention corresponding to each target text, so as to obtain a plurality of target intentions.
A determining module 206, configured to obtain the intention type of each target intention, and determine a target operation policy according to the intention type of each target intention.
For example, the intention type includes at least one of an ending type intention, a trunk type intention, and an objection type intention, wherein the objection type intention includes at least one of a resolvable type intention, an unresolved type intention, and an unsolved type intention; the determining module 204 is further configured to: determining the target operation strategy according to the intention type of each target intention and the preconfigured operation priority; the operation priority is the priority execution right of the operation flow of each target intention, and the order of intention types corresponding to the operation priority is as follows: end type intention, unsolvable type intention, trunk type intention, resolvable type intention, and unsolvable type intention.
Illustratively, the determining module 206 is further configured to: when the ending intent exists in the intent type of each of the target intents, the target operation policy is: and executing the operation flow of the ending type intention.
Illustratively, the determining module 206 is further configured to: when the ending type intention does not exist in the intention types of the target intents, judging whether the objection type intention exists or not; if the objection type intention exists, detecting whether the objection type intention comprises the resolvable type intention; if the objection type intent includes the resolvable intent, the target operational policy is: preferentially executing the operation flow of the resolvable intent, and then executing one of the operation flow of the unresolved intent, the operation flow of the main-type intent and the operation flow of the unresolved intent according to the operation priority; and if the objection type intent does not include the resolvable intent, the target operational policy is: and executing one operation flow of the unresolved type intention, the operation flow of the main type intention and the operation flow of the unresolved type intention according to the operation priority.
Illustratively, the determining module 206 is further configured to: when the operation flow with the highest current operation priority is the operation flow of the unresolved type intention and the plurality of target intents comprise a plurality of unresolved type intents arranged according to a preset sequence, executing the operation flow of the last unresolved type intention in the plurality of unresolved type intents, wherein the preset sequence comprises the position sequence of the target text corresponding to each unresolved type intention in the text to be identified; when the operation flow with the highest current operation priority is the operation flow of the main type intention, and the plurality of target intents comprise a plurality of main type intents arranged according to the preset sequence, executing the operation flow of the last main type intention in the plurality of main type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each main type intention in the text to be identified; and when the operation flow with the highest current operation priority is the operation flow of the unsolved type intention, and the plurality of target intents comprise a plurality of unsolved type intents arranged according to the preset sequence, executing the operation flow of the last unsolved type intention in the plurality of unsolved type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each unsolved type intention in the text to be identified.
An execution module 208 is configured to determine one or more operation flows based on the target operation policy, to execute a response operation based on the one or more operation flows.
The response operation includes a play operation and a follow-up operation, wherein each operation flow of the intention type corresponds to one play operation, and each play operation corresponds to one follow-up operation; the execution module 208 is further configured to: executing corresponding playing operation according to each operation flow; and determining and executing a subsequent operation corresponding to the last playing operation according to the last playing operation in the playing operations.
Illustratively, the multi-purpose semantic recognition-based processing system 20 further includes an upload module for uploading the target operating policy into a blockchain.
Example III
Referring to fig. 3, a hardware architecture diagram of a computer device according to a third embodiment of the present invention is shown. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with instructions set or stored in advance. The computer device 2 may be a rack server, a blade server, a tower server, or a rack server (including a stand-alone server, or a server cluster made up of multiple servers), or the like. As shown, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a semantic recognition-based multi-purpose processing system 20 communicatively coupled to each other via a system bus.
In this embodiment, the memory 21 includes at least one type of computer-readable storage medium including flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the computer device 2. Of course, the memory 21 may also include both internal storage units of the computer device 2 and external storage devices. In this embodiment, the memory 21 is typically used to store an operating system and various types of application software installed on the computer device 2, such as program codes of the multi-purpose processing system 20 based on semantic recognition according to the second embodiment. Further, the memory 21 may be used to temporarily store various types of data that have been output or are to be output.
The processor 22 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 22 is typically used to control the overall operation of the computer device 2. In this embodiment, the processor 22 is configured to execute the program code or the processing data stored in the memory 21, for example, execute the multi-purpose processing system 20 based on semantic recognition, so as to implement the multi-purpose processing method based on semantic recognition according to the first embodiment.
The network interface 23 may comprise a wireless network interface or a wired network interface, which network interface 23 is typically used for establishing a communication connection between the computer apparatus 2 and other electronic devices. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be an Intranet (Intranet), the Internet (Internet), the Global System for Mobile communications (Global System of Mobile communicatI/On, GSM), wideband code division multiple Access (Wideband Code DivisI/On Multiple Access, WCDMA), 4G network, 5G network, bluetooth (Bluetooth), wi-Fi, or other wireless or wireline network.
It is noted that fig. 3 only shows a computer device 2 having components 20-23, but it is understood that not all of the illustrated components are required to be implemented, and that more or fewer components may alternatively be implemented.
In the present embodiment, the multi-purpose processing system 20 based on semantic recognition stored in the memory 21 may also be divided into one or more program modules stored in the memory 21 and executed by one or more processors (the processor 22 in the present embodiment) to complete the present invention.
For example, fig. 2 shows a schematic diagram of a program module of the semantic recognition-based multi-purpose processing system 20 according to the second embodiment of the present invention, where the semantic recognition-based multi-purpose processing system 20 may be divided into a receiving module 200, a splitting module 202, an identifying module 204, a determining module 206, and an executing to module 208. Program modules in the present invention are understood to mean a series of computer program instruction segments capable of performing a specific function, more preferably than a program, for describing the execution of the semantic recognition based multi-purpose processing system 20 in a computer device 2. The specific functions of the program modules 200-208 are described in detail in the second embodiment, and are not described herein.
Example IV
The present embodiment also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs the corresponding functions. The computer readable storage medium of the present embodiment is used for the semantic recognition based multi-intent processing system 20, which when executed by a processor implements the semantic recognition based multi-intent processing method of the first embodiment.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A multi-intent processing method based on semantic recognition, the method comprising:
receiving voice to be recognized, and performing transcription operation on the voice to be recognized to obtain text to be recognized;
splitting the text to be identified into a plurality of target texts;
identifying target intentions corresponding to each target text through a pre-trained semantic identification model so as to obtain a plurality of target intentions;
obtaining the intention type of each target intention, and determining a target operation strategy according to the intention type of each target intention; a kind of electronic device with high-pressure air-conditioning system
Determining one or more operational flows based on the target operational policy to perform a responsive operation based on the one or more operational flows;
wherein the intent type includes at least one of an ending type intent, a backbone type intent, and an objection type intent, wherein the objection type intent includes at least one of a resolvable type intent, an unresolved type intent, and an unsolved type intent;
the step of determining a target operation strategy according to the intention type of each target intention comprises the following steps:
determining the target operation strategy according to the intention type of each target intention and the preconfigured operation priority;
The operation priority is an execution sequence corresponding to the operation flow of each target intention, and the execution sequence of each operation flow is as follows: an operation flow of ending type intention, an operation flow of failing to solve type intention, an operation flow of backbone type intention, an operation flow of resolvable type intention, an operation flow of not having to solve type intention;
wherein the step of determining a target operation policy according to the intention type of each target intention comprises the following steps:
when the ending type intention does not exist in the intention types of the target intents, judging whether the objection type intention exists or not;
if the objection type intention exists, detecting whether the objection type intention comprises the resolvable type intention;
if the objection type intention comprises the resolvable intention, preferentially executing the operation flow of the resolvable intention, and then executing the operation flow of the unresolved intention, the operation flow of the trunk type intention and the operation flow of the unresolved intention according to the operation priority, wherein the operation flow with the highest current operation priority is determined to be the target operation strategy; a kind of electronic device with high-pressure air-conditioning system
If the objection type intention does not comprise the resolvable type intention, determining an operation flow executing the unresolved type intention according to the operation priority, an operation flow of the trunk type intention and an operation flow without the resolvable type intention, wherein the operation flow with the highest current operation priority is used as the target operation policy;
The step of executing the operation flow with the unresolved type intention, the operation flow with the backbone type intention and the operation flow without the resolvable type intention, which is the operation flow with the highest current operation priority, according to the operation priority includes:
when the operation flow with the highest current operation priority is the operation flow of the unresolved type intention and the plurality of target intents comprise a plurality of unresolved type intents arranged according to a preset sequence, executing the operation flow of the last unresolved type intention in the plurality of unresolved type intents, wherein the preset sequence comprises the position sequence of the target text corresponding to each unresolved type intention in the text to be identified;
when the operation flow with the highest current operation priority is the operation flow of the main type intention, and the plurality of target intents comprise a plurality of main type intents arranged according to the preset sequence, executing the operation flow of the last main type intention in the plurality of main type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each main type intention in the text to be identified; a kind of electronic device with high-pressure air-conditioning system
When the operation flow with the highest current operation priority is the operation flow of the unsolved type intention, and the plurality of target intents comprise a plurality of unsolved type intents arranged according to the preset sequence, executing the operation flow of the last unsolved type intention in the plurality of unsolved type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each unsolved type intention in the text to be identified.
2. The semantic recognition-based multi-intent processing method as claimed in claim 1, wherein said step of determining a target operation policy according to intention type of each of said target intents includes:
when the ending type intents exist in the intention types of the respective target intents, determining an operation flow for executing the ending type intents as the target operation policy.
3. The semantic recognition-based multi-intent processing method of any one of claims 1 to 2, wherein the responsive operation includes a play operation and a follow-up operation, wherein an operation flow of each intent type corresponds to one play operation, and each play operation corresponds to one follow-up operation;
The step of determining one or more operation flows based on the target operation policy to perform a responsive operation based on the one or more operation flows includes:
executing corresponding playing operation according to each operation flow; a kind of electronic device with high-pressure air-conditioning system
And determining and executing a follow-up operation corresponding to the last play operation according to the last play operation in the play operations.
4. The semantic recognition-based multi-intent processing method as claimed in any one of claims 1 to 2, further comprising: uploading the target operating policy to a blockchain.
5. A multi-intent processing system based on semantic recognition, comprising:
the receiving module is used for receiving the voice to be recognized and performing transcription operation on the voice to be recognized to obtain a text to be recognized;
the splitting module is used for splitting the text to be identified into a plurality of target texts;
the recognition module is used for recognizing the target intention corresponding to each target text through a pre-trained semantic recognition model so as to obtain a plurality of target intentions;
the determining module is used for obtaining the intention type of each target intention and determining a target operation strategy according to the intention type of each target intention; a kind of electronic device with high-pressure air-conditioning system
An execution module to determine one or more operational flows based on the target operational policy to perform a responsive operation based on the one or more operational flows;
wherein the intent type includes at least one of an ending type intent, a backbone type intent, and an objection type intent, wherein the objection type intent includes at least one of a resolvable type intent, an unresolved type intent, and an unsolved type intent;
the step of determining a target operation strategy according to the intention type of each target intention comprises the following steps:
determining the target operation strategy according to the intention type of each target intention and the preconfigured operation priority;
the operation priority is an execution sequence corresponding to the operation flow of each target intention, and the execution sequence of each operation flow is as follows: an operation flow of ending type intention, an operation flow of failing to solve type intention, an operation flow of backbone type intention, an operation flow of resolvable type intention, an operation flow of not having to solve type intention;
wherein the step of determining a target operation policy according to the intention type of each target intention comprises the following steps:
when the ending type intention does not exist in the intention types of the target intents, judging whether the objection type intention exists or not;
If the objection type intention exists, detecting whether the objection type intention comprises the resolvable type intention;
if the objection type intention comprises the resolvable intention, preferentially executing the operation flow of the resolvable intention, and then executing the operation flow of the unresolved intention, the operation flow of the trunk type intention and the operation flow of the unresolved intention according to the operation priority, wherein the operation flow with the highest current operation priority is determined to be the target operation strategy; a kind of electronic device with high-pressure air-conditioning system
If the objection type intention does not comprise the resolvable type intention, determining an operation flow executing the unresolved type intention according to the operation priority, an operation flow of the trunk type intention and an operation flow without the resolvable type intention, wherein the operation flow with the highest current operation priority is used as the target operation policy;
the step of executing the operation flow with the unresolved type intention, the operation flow with the backbone type intention and the operation flow without the resolvable type intention, which is the operation flow with the highest current operation priority, according to the operation priority includes:
when the operation flow with the highest current operation priority is the operation flow of the unresolved type intention and the plurality of target intents comprise a plurality of unresolved type intents arranged according to a preset sequence, executing the operation flow of the last unresolved type intention in the plurality of unresolved type intents, wherein the preset sequence comprises the position sequence of the target text corresponding to each unresolved type intention in the text to be identified;
When the operation flow with the highest current operation priority is the operation flow of the main type intention, and the plurality of target intents comprise a plurality of main type intents arranged according to the preset sequence, executing the operation flow of the last main type intention in the plurality of main type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each main type intention in the text to be identified; a kind of electronic device with high-pressure air-conditioning system
When the operation flow with the highest current operation priority is the operation flow of the unsolved type intention, and the plurality of target intents comprise a plurality of unsolved type intents arranged according to the preset sequence, executing the operation flow of the last unsolved type intention in the plurality of unsolved type intents, wherein the preset sequence also comprises the position sequence of the target text corresponding to each unsolved type intention in the text to be identified.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program, when executed by the processor, implements the steps of the semantic recognition based multi-purpose processing method according to any of claims 1 to 4.
7. A computer-readable storage medium, in which a computer program is stored, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of the semantic recognition based multi-purpose processing method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435537.0A CN113158692B (en) | 2021-04-22 | 2021-04-22 | Semantic recognition-based multi-intention processing method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435537.0A CN113158692B (en) | 2021-04-22 | 2021-04-22 | Semantic recognition-based multi-intention processing method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113158692A CN113158692A (en) | 2021-07-23 |
| CN113158692B true CN113158692B (en) | 2023-09-12 |
Family
ID=76869466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110435537.0A Active CN113158692B (en) | 2021-04-22 | 2021-04-22 | Semantic recognition-based multi-intention processing method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158692B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017218275A1 (en) * | 2016-06-13 | 2017-12-21 | Microsoft Technology Licensing, Llc | Intelligent virtual keyboards |
| CN110309170A (en) * | 2019-07-02 | 2019-10-08 | 北京大学 | A kind of Task takes turns the complicated intension recognizing method in dialogue more |
| CN110334201A (en) * | 2019-07-18 | 2019-10-15 | 中国工商银行股份有限公司 | A kind of intension recognizing method, apparatus and system |
| CN110909137A (en) * | 2019-10-12 | 2020-03-24 | 平安科技（深圳）有限公司 | Information pushing method and device based on man-machine interaction and computer equipment |
| CN111259625A (en) * | 2020-01-16 | 2020-06-09 | 平安科技（深圳）有限公司 | Intention recognition method, device, equipment and computer readable storage medium |
| CN111368085A (en) * | 2020-03-05 | 2020-07-03 | 北京明略软件系统有限公司 | Recognition method and device of conversation intention, electronic equipment and storage medium |
| CN111400438A (en) * | 2020-02-21 | 2020-07-10 | 镁佳(北京)科技有限公司 | Method and device for identifying multiple intentions of user, storage medium and vehicle |
| CN111738016A (en) * | 2020-06-28 | 2020-10-02 | 中国平安财产保险股份有限公司 | Multi-intention recognition method and related equipment |
| CN111783471A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Semantic recognition method, device, equipment and storage medium of natural language |
| CN111930950A (en) * | 2020-09-18 | 2020-11-13 | 深圳追一科技有限公司 | Multi-intention response method, device, computer equipment and storage medium |
| CN112163086A (en) * | 2020-10-30 | 2021-01-01 | 海信视像科技股份有限公司 | Multi-intention recognition method and display device |
| CN112214588A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Multi-intention recognition method and device, electronic equipment and storage medium |
| WO2021051521A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Response information obtaining method and apparatus, computer device, and storage medium |
-
2021
- 2021-04-22 CN CN202110435537.0A patent/CN113158692B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109313534A (en) * | 2016-06-13 | 2019-02-05 | 微软技术许可有限责任公司 | Intelligent virtual keyboard |
| WO2017218275A1 (en) * | 2016-06-13 | 2017-12-21 | Microsoft Technology Licensing, Llc | Intelligent virtual keyboards |
| CN110309170A (en) * | 2019-07-02 | 2019-10-08 | 北京大学 | A kind of Task takes turns the complicated intension recognizing method in dialogue more |
| CN110334201A (en) * | 2019-07-18 | 2019-10-15 | 中国工商银行股份有限公司 | A kind of intension recognizing method, apparatus and system |
| WO2021051521A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Response information obtaining method and apparatus, computer device, and storage medium |
| CN110909137A (en) * | 2019-10-12 | 2020-03-24 | 平安科技（深圳）有限公司 | Information pushing method and device based on man-machine interaction and computer equipment |
| CN111259625A (en) * | 2020-01-16 | 2020-06-09 | 平安科技（深圳）有限公司 | Intention recognition method, device, equipment and computer readable storage medium |
| CN111400438A (en) * | 2020-02-21 | 2020-07-10 | 镁佳(北京)科技有限公司 | Method and device for identifying multiple intentions of user, storage medium and vehicle |
| CN111368085A (en) * | 2020-03-05 | 2020-07-03 | 北京明略软件系统有限公司 | Recognition method and device of conversation intention, electronic equipment and storage medium |
| CN111738016A (en) * | 2020-06-28 | 2020-10-02 | 中国平安财产保险股份有限公司 | Multi-intention recognition method and related equipment |
| CN111783471A (en) * | 2020-06-29 | 2020-10-16 | 中国平安财产保险股份有限公司 | Semantic recognition method, device, equipment and storage medium of natural language |
| CN111930950A (en) * | 2020-09-18 | 2020-11-13 | 深圳追一科技有限公司 | Multi-intention response method, device, computer equipment and storage medium |
| CN112214588A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Multi-intention recognition method and device, electronic equipment and storage medium |
| CN112163086A (en) * | 2020-10-30 | 2021-01-01 | 海信视像科技股份有限公司 | Multi-intention recognition method and display device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113158692A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3451328B1 (en) | Method and apparatus for verifying information | |
| US11217236B2 (en) | Method and apparatus for extracting information | |
| EP2869298A1 (en) | Information identification method and apparatus | |
| JP2020505643A (en) | Voice recognition method, electronic device, and computer storage medium | |
| CN111858892B (en) | Voice interaction method, device, equipment and medium based on knowledge graph | |
| CN109462482B (en) | Voiceprint recognition method, voiceprint recognition device, electronic equipment and computer readable storage medium | |
| CN110266900B (en) | Method and device for identifying customer intention and customer service system | |
| CN112633003A (en) | Address recognition method and device, computer equipment and storage medium | |
| CN111883140A (en) | Authentication method, device, equipment and medium based on knowledge graph and voiceprint recognition | |
| CN112836521A (en) | Question-answer matching method and device, computer equipment and storage medium | |
| CN111708866A (en) | Session segmentation method and device, electronic equipment and storage medium | |
| CN111768789B (en) | Electronic equipment, and method, device and medium for determining identity of voice generator of electronic equipment | |
| CN107622769B (en) | Number modification method and device, storage medium and electronic equipment | |
| CN113158692B (en) | Semantic recognition-based multi-intention processing method, system, equipment and storage medium | |
| CN112669850A (en) | Voice quality detection method and device, computer equipment and storage medium | |
| WO2023050669A1 (en) | Neural network-based information pushing method and system, device, and medium | |
| CN115858776B (en) | Variant text classification recognition method, system, storage medium and electronic equipment | |
| CN112992151B (en) | Speech recognition method, system, device and readable storage medium | |
| CN111970311B (en) | Session segmentation method, electronic device and computer readable medium | |
| CN113630309B (en) | Robot conversation system, method, device, computer equipment and storage medium | |
| CN113656566A (en) | Intelligent dialogue processing method and device, computer equipment and storage medium | |
| CN115691503A (en) | Voice recognition method and device, electronic equipment and storage medium | |
| CN114724561A (en) | Voice interruption method and device, computer equipment and storage medium | |
| CN114157763A (en) | Information processing method and device in interactive process, terminal and storage medium | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method |
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 |