WO2018205704A1 - Electronic device, intelligent voice navigation method and computer readable storage medium - Google Patents

Abstract

Provided are an electronic device, an intelligent voice navigation method and a computer readable storage medium, the intelligent voice navigation method comprising: receiving voice data inputted by a user (S10); converting the received voice data into text information, and analyzing whether the text information comprises a predetermined service keyword (S20); when the text information comprises a predetermined service keyword, parsing core viewpoint information corresponding to the text information by using a predetermined analysis rule (S40); determining whether there is a service node which corresponds to the parsed core viewpoint information according to a predetermined mapping relationship between the core viewpoint information and the service node (S50); and when there is a service node which corresponds to the parsed core viewpoint information, transferring a current service flow to the service node which corresponds to the parsed core viewpoint information (S60). The recognition success rate of an intelligent voice navigation system is thus improved.

Description

Electronic device, intelligent voice navigation method and computer readable storage medium

The present application is based on the priority of the Chinese Patent Application entitled "Intelligent Voice Navigation Method, Apparatus and Storage Medium" filed on May 10, 2017, filed on May 10, 2017, the entire contents of which is hereby incorporated by reference. The way is combined in this application.

Technical field

The present application relates to the field of intelligent voice technologies, and in particular, to an electronic device, an intelligent voice navigation method, and a computer short storage medium.

Background technique

The existing intelligent voice navigation system usually recognizes the user's voice input and transfers the user flow to the corresponding business service node according to the recognized statement. Since the user voice input statement is not necessarily a standardized statement, the system often fails. Identification, which seriously affects the navigation effect; therefore, how to improve the recognition success rate of the intelligent voice navigation system becomes an urgent problem to be solved.

Summary of the invention

The main purpose of the present application is to provide an electronic device, an intelligent voice navigation method, and a computer short storage medium, which aim to improve the recognition success rate of the intelligent voice navigation system.

A first aspect of the present application provides an electronic device including a memory and a processor, the memory storing an intelligent voice navigation system operable on the processor, the processor executing the smart voice The following steps are implemented when navigating the system:

Receiving voice data input by a user;

Converting the received voice data into text information, and analyzing whether the text information contains a predetermined business keyword; and

If the text information includes a predetermined business keyword, the business service node corresponding to the business keyword in the text information is determined by the mapping relationship between the predetermined business keyword and the service service node, and the current service process is Flow to the determined business service node.

A second aspect of the present application provides an electronic device including a memory and a processor, the memory storing an intelligent voice navigation system operable on the processor, the processor executing the smart voice The following steps are implemented when navigating the system:

Receiving voice data input by a user;

Converting the received voice data into text information, and analyzing whether the text information includes a predetermined business keyword;

When the text information includes a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule;

Determining whether there is a service service node corresponding to the parsed core viewpoint information according to a predetermined mapping relationship between the core viewpoint information and the service service node; and

When there is a service service node corresponding to the parsed core viewpoint information, the current service flow is flowed to the service service node corresponding to the parsed core viewpoint information.

A third aspect of the present application provides an intelligent voice navigation method, the method comprising the steps of:

Receiving voice data input by a user;

Converting the received voice data into text information, and analyzing whether the text information includes a predetermined business keyword;

When the text information includes a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule;

Determining whether there is a service service node corresponding to the parsed core viewpoint information according to a predetermined mapping relationship between the core viewpoint information and the service service node; and

When there is a service service node corresponding to the parsed core viewpoint information, the current service flow is flowed to the service service node corresponding to the parsed core viewpoint information.

A fourth aspect of the present application provides a computer readable storage medium storing an intelligent voice navigation system executable by at least one processor to implement the following steps:

Receiving voice data input by a user;

Converting the received voice data into text information, and analyzing whether the text information includes a predetermined business keyword;

If the text information includes a predetermined business keyword, the business service node corresponding to the business keyword in the text information is determined by the mapping relationship between the predetermined business keyword and the service service node, and the current service process is Flow to the determined business service node.

The present application can find a service keyword converted in the text information converted according to the voice data input by the user, so that the service flow can be transferred to the corresponding service service node according to the preset mapping relationship table, so that the user performs the The required business processing; does not need to analyze the meaning of the whole sentence, even when the sentence input by the user is not standardized, it can accurately identify the business demand expressed by the user, and the recognition success rate is high.

DRAWINGS

1 is a schematic diagram of a preferred embodiment of an operating environment of an intelligent voice navigation system of the present application.

FIG. 2 is a schematic structural diagram of a module of an embodiment of the intelligent voice navigation system of the present application.

FIG. 3 is a schematic structural diagram of a module of a second embodiment of the intelligent voice navigation system of the present application.

FIG. 4 is a schematic structural diagram of a parsing sub-module in the second embodiment of the intelligent voice navigation system of the present application.

FIG. 5 is a schematic structural diagram of a predetermined structure word segmentation tree.

6 is a schematic structural diagram of a module of a third embodiment of the intelligent voice navigation system of the present application;

FIG. 7 is a flowchart of an embodiment of a method for intelligent voice navigation according to the present application.

FIG. 8 is a flowchart of a second embodiment of a method for intelligent voice navigation according to the present application.

detailed description

The principles and features of the present application are described in the following with reference to the accompanying drawings, which are only used to explain the present application and are not intended to limit the scope of the application.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a preferred embodiment of an operating environment of the intelligent voice navigation system 10 of the present application.

In the present embodiment, the intelligent voice navigation system 10 is installed and operated in the electronic device 1. The electronic device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server. The electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13. Figure 1 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.

The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk or memory of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 is used to store application software and various types of data installed in the electronic device 1, such as program codes of the intelligent voice navigation system 10. The memory 11 can also be used to temporarily store data that has been output or is about to be output.

The processor 12, in some embodiments, may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing intelligent voice navigation. System 10 and so on.

The display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like in some embodiments. The display 13 is for displaying information processed in the electronic device 1 and a user interface for displaying visualization. The components 11-13 of the electronic device 1 communicate with one another via a system bus.

The intelligent voice navigation system 10 of the present application is mainly applied to a telephone service platform of an enterprise, and identifies and analyzes the service demand of the incoming user through the intelligent voice navigation system 10, and automatically transfers the user flow to the corresponding service service node for business processing, Significantly reduce the workload of agents in the call center, reduce labor costs, and increase efficiency.

As shown in FIG. 2, FIG. 2 is a schematic structural diagram of a module of an intelligent voice navigation system 10 according to an embodiment of the present application. In this embodiment, the intelligent voice navigation system 10 includes:

The receiving module 101 is configured to receive voice data input by the user; after the incoming user is connected, the intelligent voice navigation system 10 can guide the user to speak the business requirement by broadcasting the prompt, for example, the prompt is: “You can pass Speaking to handle business, such as auto insurance, life insurance, credit card, etc.; the user speaks the business demand by saying that the receiving module 101 receives the voice data generated by the user's speech.

The identification module 102 is configured to convert the received voice data into text information, and analyze whether the text information includes a predetermined business keyword; wherein, the business keyword, for example, life insurance, auto insurance, credit card, etc.; The module 102 converts the voice data received by the receiving module 101 into text information according to the voice database, and compares the predetermined business keyword with the text information to confirm whether there is a predetermined business key in the text information. word. For example, the text information converted by the identification module 102 is “I need to report the credit card”, and the identification module 102 matches the predetermined business keyword and the text information to obtain a predetermined business keyword contained in the text information. For "credit card".

The first execution module 103 is configured to determine, according to a mapping relationship between the predetermined business keyword and the service service node, the corresponding business keyword in the text information, when the text information includes the predetermined business keyword The service service node forwards the current service process to the determined service service node.

The intelligent voice navigation system 10 has a mapping relationship between a predetermined service keyword and a service service node. When the text information includes a predetermined service keyword, the first execution module 103 analyzes the data according to the identification module 102. The predetermined business keyword in the text information determines the corresponding service service node, and transfers the current service process flow to the determined service service node for the user to perform the required service processing. For example, if the predetermined business keyword included in the text information (I need to report the credit card) is a credit card, the first execution module 103 finds the service service node corresponding to the credit card by searching the mapping relationship table, and streams the current service process. The business service node corresponding to the credit card enables the user to handle the credit card related business. When the identification module 102 determines that the text information does not include a predetermined business keyword, the identification information may be sent to the background agent terminal to enable the background agent to confirm according to the text information. Business service nodes; of course, other processes can also be employed, such as transferring the current service flow to the button menu service, allowing the user to select the desired service by pressing a button, and the like.

In the solution of the intelligent voice navigation system 10 of the present embodiment, the service flow can be transferred according to the preset mapping relationship table by finding a predetermined business keyword in the text information converted according to the voice data input by the user. The corresponding business service node enables the user to perform the required business processing; the analysis of the meaning of the entire sentence is not required, and even when the sentence input by the user is not standardized, the business requirement expressed by the user can be accurately identified, and the identification is successful. The rate is high.

As shown in FIG. 3, FIG. 3 is a schematic structural diagram of a module of a second embodiment of the intelligent voice navigation system 10 of the present application. The solution of this embodiment replaces the first execution module 103 with the second execution module 108, where the second execution module 108 includes:

The parsing sub-module 104 is configured to parse the core viewpoint information corresponding to the text information by using a predetermined analysis rule when the text information includes a predetermined business keyword; the core viewpoint information is to include a predetermined business key The specific business branch direction of the word; for example, in the text message "I need to report the credit card", the business keyword is "credit card", the core view information is "loss credit card"; in the text information about the credit card, including "credit card" The core point of view information is also to apply for a credit card, open a credit card, reissue a credit card, cancel a credit card, and so on. The intelligent voice navigation system 10 is provided with a predetermined analysis rule for analyzing the text information, and the analysis sub-module 104 parses the core viewpoint information corresponding to the text information by using the predetermined analysis rule, thereby obtaining a more explicit user. Business needs.

The determining sub-module 105 is configured to determine, according to the mapping relationship between the predetermined core view information and the service service node, whether there is a service service node corresponding to the parsed core view information; each predetermined one is set in the smart voice navigation system 10 After the analysis sub-module 104 parses the core viewpoint information in the text information, the determination sub-module 105 searches for and matches the parsed core viewpoint information by the look-up table 104 after the parsing sub-module 104 parses the core viewpoint information in the text information. The service service node determines whether there is a service service node corresponding to the parsed core opinion information. For example, the business branches corresponding to the predetermined business keyword "credit card" are: "application credit card", "open credit card", "loss credit card", "replace credit card" and "debit credit card", mapping of the intelligent voice navigation system 10 The relationship table has the service service node corresponding to each of the service branches; if the core view information parsed by the parsing sub-module 104 from the text information is a "loss of credit card", the determining sub-module 105 can find the "loss of credit card" by looking up the table. The service service node determines that there is a service service node corresponding to the parsed core viewpoint information; if the core viewpoint information parsed by the parsing submodule 104 from the text information is "delete credit card", the determining submodule 105 passes the lookup table. The service service node corresponding to the "delete credit card" cannot be found, that is, it is determined that there is no service service node corresponding to the parsed core viewpoint information.

The flow rotor module 106 is configured to: when the service service node corresponding to the parsed core view information exists, stream the current service process to the service service node corresponding to the parsed core view information; and when the determining submodule 105 passes the lookup table The service service node corresponding to the parsed core viewpoint information is found, that is, the service service node corresponding to the parsed core viewpoint information exists, and the flow rotor module 106 flows the current service flow to the corresponding service service found by the determination submodule 105. Node, for the user to carry out the business processing of the demand.

The intelligent voice navigation system 10 of the present embodiment further analyzes the core viewpoint information in the text information when determining that the converted text information includes a predetermined business keyword, so as to more accurately identify a specific service branch required by the user. And find the service service node corresponding to the service branch, thereby accurately transferring the user flow to the service service node corresponding to the required service branch, and immediately performing service processing, thereby further reducing the call duration and improving the processing efficiency.

As shown in FIG. 4, in this embodiment, the parsing submodule 104 includes:

The word segmentation unit 1041 is configured to perform segmentation on the text information according to a predetermined word segmentation rule when the text information includes a predetermined business keyword, that is, the word information is cut into a plurality of words or phrases; preferably, The predetermined word segmentation rule is: a long word priority principle. The long-word priority principle refers to: for a short sentence T1 that requires a word segmentation, start with the first word A, find a longest word X1 starting from A from the pre-stored thesaurus, and then remove it from T1. X1 has T2 left, and the same segmentation principle is applied to T2. The result after segmentation is “X1/X2/, ,,,,,”, for example, for the text message “I need to report the credit card”, the result of the word segmentation is "I", "need", "loss", "credit card".

The tagging unit 1042 is configured to perform part-of-speech tagging on the segmentation result according to a predetermined part-of-speech tagging rule; for example, the part-of-speech tagging of the segmentation result of the text message “I need to report the credit card” may be: “I/pronoun”, “need/verb” ", loss reporting / verb", "credit card / noun".

Preferably, the predetermined part-of-speech tagging rule is: according to the mapping relationship between words and words in the universal word dictionary library and part of speech (for example, in the universal word dictionary library, "credit card" and "life insurance" correspond to nouns, "loss" "Opening" corresponds to the verb), and/or, according to the mapping relationship between the preset words and words and the part of speech (for example, the mapping relationship between the preset words and words and the part of speech, "credit card", " "Life insurance" corresponds to business terms, "loss" and "opening" correspond to business verbs), and determine the part of speech corresponding to each participle after word segmentation, and mark it. Wherein, the word-to-word tagging can be performed separately by using the mapping relationship between words and words in the universal word dictionary library and the part of speech, or the word-to-speech relationship between the preset words and words and the part of speech can be separately used, or the above two mapping relationships can be used at the same time. The part-of-speech tagging is performed, wherein the part-of-speech tagging relationship between the preset word and the word and the part of speech is higher than the word-to-speech relationship between the word and the word in the universal word dictionary library (for example, in the universal word dictionary library, "credit card" "Life insurance" corresponds to the noun, "credit card", the default word and word mapping relationship with the part of speech, "credit card", "life insurance" corresponds to the business noun, at this time will be "credit card", "life insurance" "Marked as a business term."

The constructing unit 1043 is configured to construct each participle corresponding to the text information into a preset structure word segmentation tree according to the order and part of speech of each word segment corresponding to the text information;

As shown in FIG. 5, the preset structure word segmentation tree includes a multi-level node, the first-level node is the text information itself, the second-level node is a word segmentation phrase, and each level node after the second-level node is The word segmentation phrase of the upper-level node is obtained according to the part of speech, that is, each level node after the second-level node is the next-level word segmentation or participle phrase corresponding to the upper-level node. The process of constructing each word segment corresponding to the text information into a preset structure word segment according to the order and part of speech of the word segment corresponding to the text information specifically includes: A1, in each word segment corresponding to the text information, Finding a target participle of each predetermined part of speech (eg, noun, verb, etc.); A2, determining a participle phrase corresponding to each second level node according to the order of each target participle corresponding to the text information (preferably, A2 includes: The word before the next target participle is used as the participle phrase of the previous target participle; the last target participle and the following words are used as the last participle phrase); A3, if a participle phrase cannot be further divided, then the The participle phrase is the last level node of the branch of the node; A4, if a participle phrase can further segment the word, find the target participle of each predicate part of the participle phrase, and according to the order of each target participle corresponding to the participle phrase Determining a participle or a participle phrase corresponding to the next-level node of the participle phrase; A5, repeating the above steps Steps A3 and A4 until the word segment corresponding to the last-level node of each node branch is determined. For example, the "prepared structure segmentation tree" constructed by "I went to the playground to play football" is shown in Figure 5.

The parsing unit 1044 is configured to parse the core viewpoint information corresponding to the text information based on the preset structure word segmentation tree.

After the constructing unit 1043 constructs the preset structure word segmentation tree of the text information, the parsing unit 1044 calculates each first preset part-of-speech participle (for example, a business noun) and each second pre-preparation based on the preset structure segmentation tree. Setting the distance of the part-of-speech participle (for example, a verb or a business verb) (ie, the number of nodes separated by each first pre-determined part-of-speech participle and each second pre-determined part-of-speech participle is the distance); The preset part-of-speech participle is separated from the nearest second predicate part-of-speech participle, and the respective first pre-determined part-of-speech participle and the second pre-determined part-of-speech participle which are closest to each other are respectively composed of core viewpoint information corresponding to the order in the text information.

As shown in FIG. 6, the intelligent voice navigation system 10 of the embodiment further includes: a switching module 107, configured to not include a predetermined service keyword in the text information, or When the core view information corresponds to the service service node, the text information is sent to the background agent terminal, and the background agent manually determines the service service node according to the text information.

In the voice data input by the user, there may be cases where the user does not directly refer to the business keyword/core view information, but only describes his or her own needs, or the user does not say the business keyword/core view information, etc.; The system can not find the business keyword/core view information, so that the corresponding service service node cannot be determined. In this case, the transfer module 107 sends the text information to the background agent terminal, allowing the background agent to go. Analyze and understand the user's business requirements to determine the corresponding service service node. The background agent terminal can feed the determined service service node to the intelligent voice navigation system 10 through the switching module 107, thereby transferring the service flow to the corresponding service service node. The service processing; the intelligent voice navigation system 10 can further improve the recognition success rate of the user voice input by cooperating with the background agent terminal. Of course, when the intelligent voice system does not process the sent text information in time (ie, when the feedback of the background agent terminal is not received in time), the intelligent voice system can directly transfer the service flow to the button menu service or perform other processing. In addition, in other embodiments, the intelligent voice system may also directly transfer the case menu service when the text information does not contain a predetermined service keyword or if there is no service service node corresponding to the parsed core viewpoint information. Or other processing.

The present application also proposes an intelligent voice navigation method that can be performed by the above-described intelligent voice navigation system 10.

As shown in FIG. 7, FIG. 7 is a flowchart of an embodiment of a method for intelligent voice navigation according to the present application. The intelligent voice navigation method of this embodiment includes:

In step S10, voice data input by the user is received.

After the incoming user is connected, the prompt can be broadcasted to guide the user to speak the business demand. For example, the prompt is: “You can handle the business by speaking, such as auto insurance, life insurance, credit card, etc.”; Out of the business demand, the system receives the voice data generated by the user's speech.

Step S20: Convert the received voice data into text information, and analyze whether the text information includes a predetermined business keyword.

Among them, business keywords, for example, life insurance, auto insurance, credit card, etc.; after receiving the voice data input by the user, the system converts the received voice data identification into text information according to the voice database, and passes the predetermined business key The words are compared with the text information to confirm whether there is a predetermined business keyword in the text information. For example, the converted text information is “I need to report the credit card”, and the predetermined business keyword contained in the text information is “credit card” by matching the predetermined business keyword with the text information.

Step S30, if the text information includes a predetermined business keyword, the business service node corresponding to the business keyword in the text information is determined by a mapping relationship between the predetermined business keyword and the service service node. The current service process flows to the identified business service node.

The system has a mapping relationship table between the predetermined business keyword and the service service node. When the text information includes a predetermined business keyword, the system determines the predetermined business keyword in the text information according to the analysis. The corresponding service service node is determined, and the current service process flow is transferred to the determined service service node for the user to perform the required service processing. For example, the predetermined business keyword included in the above text information (I need to report the credit card) is a credit card, and the system finds the business service node corresponding to the credit card by searching the mapping relationship table, and transfers the current service flow to the credit card corresponding service. The service node enables the user to handle the credit card related business. After the system analyzes the text information, it is determined that the text information does not include a predetermined service keyword, and the text information may be preferably sent to the background agent terminal, so that the background agent confirms the service service node according to the text information. Of course, other processing can also be employed, for example, to transfer the current service flow to the button menu service, to allow the user to select the desired service by pressing a button, and the like.

In the scheme of the intelligent voice navigation method of the present embodiment, the predetermined service keyword converted in the text information converted according to the voice data input by the user is found, so that the service flow can be transferred to the corresponding according to the preset mapping relationship table. The business service node enables the user to perform the required business processing; it does not need to analyze the meaning of the entire sentence, even when the statement of the user's speech input is not standardized, the user's expressed business demand can be accurately identified, and the recognition success rate high.

As shown in FIG. 8, FIG. 8 is a flowchart of a second embodiment of the method for intelligent voice navigation according to the present application. The intelligent voice navigation method of this embodiment replaces step S30 in FIG. 7 with:

Step S40: If the text information includes a predetermined business keyword, the core viewpoint information corresponding to the text information is parsed by using a predetermined analysis rule.

The core view information is the specific business branch direction including the predetermined business keywords; for example, in the text message "I need to report the credit card", the business keyword is "credit card", the core view information is "loss credit card"; The text information includes the core point of view of “credit card”, as well as applying for a credit card, opening a credit card, reissuing a credit card, and canceling a credit card. A predetermined analysis rule for analyzing the text information is set in the system, and the core viewpoint information corresponding to the text information is parsed by using the predetermined analysis rule, thereby obtaining a clearer user's business requirement.

Step S50: Determine, according to the mapping relationship between the predetermined core viewpoint information and the service service node, whether there is a service service node corresponding to the parsed core viewpoint information.

In the system of the embodiment, a mapping relationship table between each service branch of each predetermined business keyword and a service service node is set, and after the core viewpoint information in the text information is parsed, the core viewpoint is found and analyzed through the lookup table. The service service node corresponding to the information determines whether there is a service service node corresponding to the parsed core opinion information. For example, the business branches corresponding to the predetermined business keyword "credit card" are: "application credit card", "open credit card", "loss credit card", "replace credit card" and "deregistration credit card", in the mapping relationship table in the system The service service node corresponding to each of the foregoing service branches; if the core view information parsed from the text information is a "loss of credit card", the business service node corresponding to the "loss of credit card" can be found by looking up the table, that is, the presence and resolution are determined. If the core viewpoint information parsed from the text information is "delete credit card", the service service node corresponding to "delete credit card" cannot be found by looking up the table, that is, the non-existence and resolution are determined. The business service node corresponding to the core view information.

Step S60: If there is a service service node corresponding to the parsed core viewpoint information, the current service flow is transferred to the service service node corresponding to the parsed core viewpoint information.

When the service service node corresponding to the parsed core viewpoint information is found through the lookup table, that is, the service service node corresponding to the parsed core viewpoint information exists, the system flows the current service flow to the found corresponding service service node, For the user to handle the business needs.

In the intelligent voice navigation method of the embodiment, when it is determined that the converted text information includes a predetermined business keyword, the core viewpoint information in the text information is further analyzed to more accurately identify a specific service branch required by the user. The service service node corresponding to the service branch is found, so that the user flow is accurately transferred to the service service node corresponding to the required service branch, and the service is processed immediately, thereby further reducing the call duration and improving the processing efficiency.

Preferably, the intelligent voice navigation method of the embodiment does not include a predetermined service keyword in the text information, or the text is not present when there is no service service node corresponding to the parsed core viewpoint information. The information is sent to the background agent terminal, and the background agent manually determines the service service node according to the text information.

In the voice data input by the user, there may be cases where the user does not directly refer to the business keyword/core view information, but only describes his or her own needs, or the user does not say the business keyword/core view information, etc.; The system can not find the business keyword/core view information, so that the corresponding service service node cannot be determined. In this case, the system will send the text information to the background agent terminal, so that the background agent can analyze and understand the user. The service needs to determine the corresponding service service node, and the background agent terminal can feed the determined service service node to the system, thereby transferring the service process flow to the corresponding service service node for service processing; and the system cooperates with the background agent terminal. The recognition success rate of the user's voice input can be further improved. Of course, when the background agent in the background does not process the sent text information in time (that is, when the feedback of the background agent terminal is not received in time), the system can directly transfer the service flow to the button menu service or perform other processing. In addition, in other embodiments, the system may also directly transfer the case menu service or other when the text information does not contain a predetermined business keyword or if there is no business service node corresponding to the parsed core opinion information. deal with.

Further, the present application further provides a computer readable storage medium storing an intelligent voice navigation system, the smart voice navigation system being executable by at least one processor to cause the at least one processing The intelligent speech navigation method in any of the above embodiments is performed.

The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structural transformation, or direct/indirect use, of the present application and the contents of the drawings is used in the application of the present application. All other related technical fields are included in the patent protection scope of the present application.

Claims (20)

1. An electronic device, comprising: a memory and a processor, the memory storing an intelligent voice navigation system operable on the processor, the processor executing the intelligent voice navigation system The following steps are implemented:

   Receiving voice data input by a user;

   Converting the received voice data into text information, and analyzing whether the text information contains a predetermined business keyword; and

   If the text information includes a predetermined business keyword, the business service node corresponding to the business keyword in the text information is determined by the mapping relationship between the predetermined business keyword and the service service node, and the current service process is Flow to the determined business service node.
2. An electronic device, comprising: a memory and a processor, the memory storing an intelligent voice navigation system operable on the processor, the processor executing the intelligent voice navigation system The following steps are implemented:

   Receiving voice data input by a user;

   Converting the received voice data into text information, and analyzing whether the text information includes a predetermined business keyword;

   When the text information includes a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule;

   Determining whether there is a service service node corresponding to the parsed core viewpoint information according to a predetermined mapping relationship between the core viewpoint information and the service service node; and

   When there is a service service node corresponding to the parsed core viewpoint information, the current service flow is flowed to the service service node corresponding to the parsed core viewpoint information.
3. The electronic device according to claim 2, wherein when the processor executes the intelligent voice navigation system, the following steps may be further implemented: when the text information does not contain a predetermined business keyword, or When there is no service service node corresponding to the parsed core viewpoint information, the text information is sent to the background agent terminal.
4. The electronic device according to claim 2, wherein said step "if the text information contains a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule "include:

   When the text information includes a predetermined business keyword, the word information is segmented according to a predetermined word segmentation rule;

   The participle results are tagged according to the predetermined part-of-speech tagging rules;

   Forming, according to the order and part of speech of each word segment corresponding to the text information, each word segment corresponding to the text information to construct a predetermined structure word segmentation tree;

   The core viewpoint information corresponding to the text information is parsed based on the preset structure word segmentation tree.
5. The electronic device according to claim 4, wherein the corresponding core viewpoint information is a distance calculated by each of the first preset part-of-speech participles and each of the second preset part-of-speech participles based on the preset structure word segmentation tree, respectively Finding a second preset part-of-speech participle that is closest to each of the first preset part-of-speech participles, and respectively composing each of the first pre-determined part-of-speech participles and the second pre-determined part-of-speech participles that are closest thereto according to the order in the text information owned.
6. The electronic device according to claim 4, wherein said predetermined part-of-speech tagging rule is:

   According to the mapping relationship between words and words in the universal word dictionary library and part of speech, and/or the mapping relationship between the preset words and words and the part of speech, the part of speech corresponding to each participle after word segmentation is determined and marked.
7. The electronic device according to claim 4, wherein said predetermined word segmentation rule is: a long word priority principle.
8. The electronic device according to claim 4, wherein the predetermined structure word segmentation tree comprises a multi-level node, the first-level node is the text information itself, and the second-level node is a word segmentation phrase, after the second-level node Each level of the node is obtained by the participle of the upper-level node according to the part of speech.
9. The electronic device according to claim 8, wherein the corresponding core viewpoint information is a distance calculated by each of the first preset part-of-speech participles and each of the second preset part-of-speech participles based on the preset structure word segmentation tree, respectively Finding a second preset part-of-speech participle that is closest to each of the first preset part-of-speech participles, and respectively composing each of the first pre-determined part-of-speech participles and the second pre-determined part-of-speech participles that are closest thereto according to the order in the text information owned.
10. An intelligent voice navigation method, characterized in that the method comprises the steps of:

    A. Receive voice data input by the user;

    B. Convert the received voice data into text information, and analyze whether the text information includes a predetermined business keyword;

    C. When the text information includes a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule;

    D. determining, according to a predetermined mapping relationship between the core view information and the service service node, whether there is a service service node corresponding to the parsed core view information; and

    E. When there is a service service node corresponding to the parsed core viewpoint information, the current service flow is flowed to the service service node corresponding to the parsed core viewpoint information.
11. The intelligent voice navigation method according to claim 10, wherein said steps C, D and E are replaced by the steps of:

    If the text information includes a predetermined business keyword, the business service node corresponding to the business keyword in the text information is determined by the mapping relationship between the predetermined business keyword and the service service node, and the current service process is Flow to the determined business service node.
12. The intelligent voice navigation method according to claim 10, wherein the intelligent voice navigation method further comprises the steps of:

    When the text information does not include a predetermined service keyword, or when there is no service service node corresponding to the parsed core viewpoint information, the text information is sent to the background agent terminal.
13. The intelligent voice navigation method according to claim 10, wherein the step "if the text information contains a predetermined business keyword, the core corresponding to the text information is parsed by using a predetermined analysis rule. Viewpoint information" includes:

    When the text information includes a predetermined business keyword, the word information is segmented according to a predetermined word segmentation rule;

    The participle results are tagged according to the predetermined part-of-speech tagging rules;

    Forming, according to the order and part of speech of each word segment corresponding to the text information, each word segment corresponding to the text information to construct a predetermined structure word segmentation tree;

    The core viewpoint information corresponding to the text information is parsed based on the preset structure word segmentation tree.
14. The intelligent voice navigation method according to claim 13, wherein the corresponding core viewpoint information is based on the preset structure word segmentation tree to calculate the distance between each first preset part-of-speech participle and each second preset part-of-speech participle Finding a second preset part-of-speech participle that is closest to each of the first preset part-of-speech participles, and respectively respectively respectively, respectively, each first pre-determined part-of-speech participle and the second pre-determined part-of-speech participle that is closest to the textual information The composition of the order is obtained.
15. The intelligent voice navigation method according to claim 13, wherein the predetermined word segmentation rule is: a long word priority principle.
16. The intelligent voice navigation method according to claim 13, wherein the predetermined part-of-speech tagging rule is: according to a mapping relationship between a word and a word in a universal word dictionary library and a part of speech, and/or a preset word sum The mapping relationship between words and part of speech is determined, and the part of speech corresponding to each participle after word segmentation is determined and marked.
17. The intelligent voice navigation method according to claim 13, wherein the preset structure word segmentation tree comprises a multi-level node, the first level node is the text information itself, the second level node is a word segmentation phrase, and the second level Each level node after the node is obtained by the participle of the upper-level node.
18. The intelligent voice navigation method according to claim 17, wherein the corresponding core viewpoint information is based on the preset structure word segmentation tree to calculate the distance between each first preset part-of-speech participle and each second preset part-of-speech participle Finding a second preset part-of-speech participle that is closest to each of the first preset part-of-speech participles, and respectively respectively, respectively, the first pre-determined part-of-speech participle and the second pre-determined part-of-speech participle that are closest to them in the order of the text information The composition is obtained.
19. A computer readable storage medium, characterized in that the computer readable storage medium stores an intelligent voice navigation system, the intelligent voice navigation system being executable by at least one processor to implement the following steps:

    F. receiving voice data input by the user;

    G. Converting the received voice data into text information, and analyzing whether the text information includes a predetermined business keyword;

    H. If the text information includes a predetermined service keyword, determining a service service node corresponding to the service keyword in the text information by using a predetermined mapping relationship between the business keyword and the service service node, The service process flows to the identified business service node.
20. The computer readable storage medium of claim 19, wherein said step H is replaced by:

    When the text information includes a predetermined business keyword, the core view information corresponding to the text information is parsed by using a predetermined analysis rule;

    Determining whether there is a service service node corresponding to the parsed core viewpoint information according to a predetermined mapping relationship between the core viewpoint information and the service service node; and

    When there is a service service node corresponding to the parsed core viewpoint information, the current service flow is transferred to the service service node corresponding to the parsed core viewpoint information.

Images