WO2020119346A1

WO2020119346A1 - Natural semantic comprehension method and apparatus, and computing device

Info

Publication number: WO2020119346A1
Application number: PCT/CN2019/116377
Authority: WO
Inventors: 孙文豹; 马世奎; 陈原; 李强
Original assignee: 深圳前海达闼云端智能科技有限公司
Priority date: 2018-12-12
Filing date: 2019-11-07
Publication date: 2020-06-18
Also published as: CN109684632A; CN109684632B

Abstract

The present application relates to the technical field of artificial intelligence, and in particular, a natural semantic comprehension method and apparatus, a computing device and a computer-readable storage medium are disclosed. The method comprises: receiving a question sentence sent by an intelligent terminal; using a pre-set word segmentation algorithm to split the question sentence into a plurality of words; searching a pre-set question and answer library for sentences which include at least one of the words; calculating similarities between the sentences and the question sentence sent by the intelligent terminal to obtain similarity values; and selecting an answer corresponding to a sentence with the highest similarity, and sending same to the intelligent terminal. It can be seen therefrom that using the solution of the present application can transfer a natural semantic comprehension task of the intelligent terminal to a cloud server for execution, thereby reducing the workload of the intelligent terminal, and improving the working efficiency.

Description

Natural semantic understanding method, device and computing equipment

Technical field

The embodiments of the present application relate to the field of artificial intelligence, and in particular, to a method, apparatus, computing device, and computer-readable storage medium for natural semantic understanding.

Background technique

Natural semantic understanding is a technology that uses natural language to communicate with smart terminals. Natural semantic understanding systems need to process large-scale real text. In the process of implementing the present application, the inventor of the present application found that the amount of calculation required for natural language understanding on an intelligent terminal is large, which affects the efficiency of natural semantic understanding.

Application content

In view of the above problems, the present application is proposed in order to provide a method, apparatus, computing device, and computer-readable storage medium for overcoming the above problems or at least partially solving the above problems.

To solve the above technical problems, a technical solution adopted by the embodiments of the present application is to provide a method for natural semantic understanding, including:

Receive question statements sent by smart terminals;

Use a preset word segmentation algorithm to split the question sentence into multiple words;

Searching for a sentence containing at least one of the words in the preset question and answer library;

Calculating the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value;

The response corresponding to the sentence with the highest similarity is selected and sent to the smart terminal.

Wherein, the method further includes: determining whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold;

If the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, the confidence index is reduced by the preset first value;

If the similarity value corresponding to the sentence with the highest similarity is not less than a preset first threshold, determine whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold;

If the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the preset second threshold, increase the confidence index by the preset second value;

Determine whether the confidence index is less than a preset third threshold;

If the confidence index is less than the preset third threshold, a manual intervention algorithm is triggered.

Wherein, the manual intervention algorithm includes:

Search for answers to question statements sent by the smart terminal;

When the answer to the question sentence is searched, the question sentence and the answer to the question sentence are stored in the preset question and answer library.

Wherein, if the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold, the response corresponding to the sentence with the highest similarity is sent to the smart terminal in a preset warning manner.

Another technical solution adopted by this application is to provide a natural semantic understanding device, including:

Receiving module: used to receive the question statement sent by the intelligent terminal;

Splitting module: used to split the question sentence into multiple words using a preset word segmentation algorithm;

Search module: used to search for a sentence containing at least one of the words in the preset question and answer library;

Calculation module: used to calculate the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value;

Sending module: used to select the reply corresponding to the sentence with the highest similarity to send to the smart terminal.

Wherein, the device further includes: a first judgment module for judging whether the similarity value corresponding to the sentence with the highest similarity is smaller than a preset first threshold; a first calculation module is used for when the highest similarity is When the similarity value corresponding to the sentence is less than the preset first threshold, the confidence index is reduced by the preset first value; the second judgment module is used when the similarity value corresponding to the sentence with the highest similarity is not less than the preset first At a threshold, determine whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold; a second calculation module is used when the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the When the second threshold is set, the confidence index is increased by a preset second value; a third judgment module is used to judge whether the confidence index is less than the preset third threshold; a trigger module is used when the confidence index is less than the preset third At three thresholds, the manual intervention algorithm is triggered.

Wherein, the manual intervention algorithm includes: searching for the answer to the question sentence sent by the smart terminal; when searching for the answer to the question sentence, storing the question sentence and the answer to the question sentence into the preset Q&A library.

If the judgment result of the first judgment module is that the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, the response corresponding to the sentence with the highest similarity is sent to all Described intelligent terminal.

Another technical solution adopted by the present application is to provide a computing device, including: a processor, a memory, a communication interface, and a communication bus, and the processor, the memory, and the communication interface communicate with each other through the communication bus Communication; the memory is used to store at least one execution instruction, and the executable instruction causes the processor to perform an operation corresponding to a method of natural semantic understanding.

Another technical solution adopted by the present application is to provide a computer-readable storage medium in which at least one execution instruction is stored, and the executable instruction causes a processor to perform an operation corresponding to a method of natural semantic understanding.

The beneficial effects of the embodiments of the present application are: different from the situation of the prior art, the embodiments of the present application can realize the transfer of the natural semantic understanding of the smart terminal to the cloud server for execution, reducing the workload of the smart terminal and improving the work efficiency; In addition, a confidence index is set to evaluate the natural semantic understanding of the intelligent terminal, and when the confidence index is low, a manual intervention algorithm is executed to modify the preset question and answer library, which improves the efficiency and accuracy of semantic understanding.

The above description is only an overview of the technical solutions of this application. In order to understand the technical means of this application more clearly, it can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of this application more obvious and understandable The specific examples of this application are listed below.

BRIEF DESCRIPTION

By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments, and are not considered to limit the present application. Furthermore, the same reference numerals are used to denote the same parts throughout the drawings. In the drawings:

FIG. 1 is a flowchart of a method for understanding natural semantics according to an embodiment of the present application;

2 is a schematic diagram of a method for natural semantic understanding according to another embodiment of the present application;

3 is a functional block diagram of a natural semantic understanding device according to an embodiment of the present application;

4 is a schematic diagram of a computing device according to an embodiment of the present application.

detailed description

Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

FIG. 1 is a flowchart of an embodiment of a natural semantic understanding method of the present application. As shown in Figure 1, the method includes the following steps:

Step S101: Receive the question statement sent by the smart terminal.

In this step, the question sentence sent by the smart terminal may be in the form of voice or text. When the question sentence sent by the smart terminal is in the form of speech, a preset text conversion algorithm is used to convert the question sentence Convert to text.

Step S102: Split the question sentence into multiple words using a preset word segmentation algorithm.

In this step, the preset word segmentation algorithm is the prior art. When splitting the question sentence, the sentence is split into a combination of several words according to the components of the word in the sentence, such as: The sentence is "what do you eat today?". When splitting, the question sentence will be split into a combination of three words "today", "eat" and "what".

Step S103: Search for a sentence containing at least one of the words in the preset question and answer library.

In this step, the form of stored sentences in the preset question and answer library is a form of one question and one answer, that is, each question has an answer to the corresponding question. The search in the preset question and answer library specifically combines the words and Match the questions in the preset question and answer library, for example, "what do you eat today?" The split words are a combination of three words "today", "eat" and "what". As the search content, the three words are matched with the questions in the preset question and answer library.

Step S104: Calculate the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value.

In this step, after a search term is matched in the preset question and answer library, the similarity between the sentence where the found word is located and the question sentence sent by the smart terminal is calculated, and the calculation algorithm is the prior art. No limitation here. For example, after the question "what do you eat today" sent by the smart terminal, after matching with the question in the preset question and answer library, one of the matched sentences is "what to eat for lunch", then the word matching degree is used as similar When calculating the degree algorithm, the question sent by the intelligent terminal and the matched sentence have a total of two words, namely "eat" and "what", the total number of word segments in the sentence is three words, so , The similarity value is 67%.

Step S105: Select the reply corresponding to the sentence with the highest similarity and send it to the smart terminal.

In this step, each sentence retrieved in the preset question and answer library is similar to the question sentence sent by the intelligent terminal, and the sentence with the highest similarity is considered to be the question sent by the intelligent terminal The sentence is the closest. Understandably, when the user enters a question sentence on the smart terminal, he hopes to get a response corresponding to the input question sentence. Therefore, the sentence with the highest similarity in the preset question and answer library is mapped to The reply is sent to the smart terminal.

The embodiment of the present application transmits the questions input by the user of the intelligent terminal to the cloud server for processing, and sends the answers corresponding to the questions entered by the user retrieved by the cloud server to the intelligent terminal. It can be seen that the use of this application reduces The workload of the smart terminal improves the work efficiency of the smart terminal in handling problems.

FIG. 2 is a flowchart of another embodiment of a natural semantic understanding method of the present application. Compared with the previous embodiment, this embodiment also includes the following steps:

Step S201: Determine whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold, if yes, perform step S202, and if not, perform step S203.

In this step, the preset first threshold is artificially set to determine the acceptable minimum value of the similarity. For example, the preset first threshold is set to 50%.

Step S202: Decrease the confidence index by the preset first value.

In this step, when the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, it means that the similarity between the sentence with the highest similarity and the question sentence sent by the smart terminal is low, and the cloud server There is no confidence recognition, so the confidence index is reduced by a preset first value, which is artificially set, for example, the preset first value is set to 25%. When the similarity value corresponding to the sentence with the highest similarity is lower than the preset first threshold by 50%, the confidence index is reduced by 25%. The confidence index has an initial value. After each time the similarity is judged, the obtained confidence index is used as the new confidence index initial value. For example, the initial value of the confidence index is 100%. For the first question sent by the smart terminal, the highest similarity value is 40%, which is 50% below the first threshold, then the confidence index is reduced by 25% to obtain new confidence. The index is 75%. When the second question is received, if the obtained similarity is still lower than the first threshold by 50%, it will be reduced by 25% on the basis of the new confidence index of 75%, and so on.

It is worth noting that when the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, when a response corresponding to the sentence with the highest similarity is returned to the smart terminal, it is displayed in a warning manner, To inform the user that the accuracy of the response is low, the warning method can be any mark that can distinguish the accuracy, for example, the non-warning reply statement is displayed in black text on a white background, and the warning statement is displayed in black text on a red background Text display.

Step S203: determine whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the preset second threshold, if yes, perform step S204, and if not, perform step S205.

In this step, the preset second threshold is used to judge the recognition degree of the problem statement sent by the smart terminal. In this step, the second threshold is set to 100%, that is, when the smart terminal sends When the question sentence of the question completely matches the sentence in the preset question and answer library, it is considered that the preset second threshold is reached.

Step S204: Increase the confidence index by a preset second value.

In this step, when the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold, it means that the similarity between the sentence with the highest similarity and the question sentence sent by the smart terminal is high, The cloud server has confidence recognition, so the confidence index is increased by a preset first value, which is manually set, for example, the preset second value is set to 15%. When the similarity value corresponding to the sentence with the highest similarity is equal to the preset second threshold 100%, the confidence index is increased by 15%.

Step S205: Determine whether the confidence index is less than a preset third threshold, and if so, perform step S206.

In this step, the preset third threshold is used to explain the acceptable minimum value of the confidence index. In the embodiment of the present application, the third threshold is set to 50%, that is, when the confidence index is less than 50 %, step S206 is executed.

Step S206: Trigger the manual intervention algorithm.

In this step, after the manual intervention algorithm is triggered, manual intervention may be prompted, or a preset algorithm may be triggered. The manual intervention or the preset algorithm specifically executes: searching for answers to question statements sent by the smart terminal; When describing the answer to the question sentence, the question sentence and the answer to the question sentence are stored in the preset question and answer library. It can be understood that the content of the manual intervention or the execution of the preset algorithm can be manually executed or can be implemented by an algorithm. When the algorithm is implemented, a related algorithm, such as a crawler algorithm, needs to be set in the cloud server in advance.

In this embodiment of the present application, the confidence index is set as the degree of understanding of the question statement sent by the intelligent terminal. When the confidence index is low, a manual intervention algorithm is triggered to include the statement that the cloud processor does not have confidence to process in the preset question and answer library , So as to assist the cloud processor to more efficiently handle the problem sent by the intelligent terminal.

FIG. 3 is a functional block diagram of an embodiment of a natural semantic understanding device of the present application. As shown in FIG. 3, the device includes a receiving module 301, a splitting module 302, a searching module 303, a calculating module 304, and a sending module 305. Among them, the receiving module 301 is used to receive the question sentence sent by the intelligent terminal; the splitting module 302 is used to split the question sentence into multiple words using a preset word segmentation algorithm; the search module 303 is used to answer questions and answers in a preset Search for sentences containing at least one of the words in the library; calculation module 304, used to calculate the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value; sending module 305, used to select the similarity The reply corresponding to the sentence with the highest degree is sent to the smart terminal.

In the embodiment of the present application, the device further includes: a first judgment module 306, a first calculation module 307, a second judgment module 308, a second calculation module 309, a third judgment module 310, and a trigger module 311. The first judgment module 306 is used to judge whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold; the first calculation module 307 is used to determine the similarity corresponding to the sentence with the highest similarity When the degree value is less than the preset first threshold, the confidence index is reduced by the preset first value; the second judgment module 308 is used when the similarity value corresponding to the sentence with the highest similarity is not less than the preset first threshold, Judging whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold; the second calculation module 309 is used when the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the preset second At the second threshold, the confidence index is increased by the preset second value; the third judgment module 310 is used to judge whether the confidence index is less than the preset third threshold; the trigger module 311 is used when the confidence index is less than the preset third At three thresholds, the manual intervention algorithm is triggered.

Among them, the manual intervention algorithm in the trigger module 311 includes: searching for answers to question statements sent by the smart terminal; when searching for answers to the question statements, storing the question statements and the answers to the question statements In the preset question and answer library.

Wherein, when the result of the first calculation module 307 determines that the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, the response corresponding to the sentence with the highest similarity is sent in a preset warning manner To the smart terminal.

In the embodiment of the present application, the receiving module receives the question statement sent by the intelligent terminal, searches the preset question and answer library for the statement matching the question statement received by the receiving module through the search module, and corresponds the most similar question statement through the sending module Sent to the smart terminal, it can be seen that through this application, the workload of the smart terminal is reduced and the work efficiency is improved; in addition, the confidence index is set to evaluate the natural semantic understanding of the smart terminal and be confident When the index is low, the manual intervention algorithm is executed to modify the preset question and answer library, which improves the efficiency and accuracy of semantic understanding.

Embodiments of the present application provide a non-volatile computer-readable storage medium, where the computer-readable storage medium stores at least one executable instruction, and the computer-executable instruction can execute a natural method in any of the foregoing method embodiments. Semantic understanding method.

FIG. 4 is a schematic structural diagram of an embodiment of a computing device of the present application. The specific embodiment of the present application does not limit the specific implementation of the computing device.

As shown in FIG. 4, the computing device may include: a processor 402, a communication interface 404, a memory 406, and a communication bus 408.

among them:

The processor 402, the communication interface 404, and the memory 406 communicate with each other through the communication bus 408.

The communication interface 404 is used to communicate with other devices.

The processor 402 is configured to execute the program 410, and may specifically execute relevant steps in the above-mentioned method embodiment of natural semantic understanding.

Specifically, the program 410 may include program code, and the program code includes computer operation instructions.

The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), for example, at least one magnetic disk memory.

The program 410 may specifically be used to cause the processor 402 to perform the following operations:

Receive question statements sent by smart terminals;

Searching for sentences containing at least one of the words in the preset question and answer library;

In an optional manner, the program 410 may be further specifically configured to cause the processor 402 to perform the following operation: determine whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold;

Determine whether the confidence index is less than a preset third threshold;

In an optional manner, the program 410 may be further specifically used to cause the processor 402 to perform the following operations:

Search for answers to question statements sent by the smart terminal;

In an optional manner, the program 410 may be further specifically configured to cause the processor 402 to perform the following operation: if the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold, then the similarity The reply corresponding to the highest sentence is sent to the smart terminal in a preset warning manner.

The algorithms and displays provided here are not inherently related to any particular computer, virtual system or other devices. Various general-purpose systems can also be used together with the teaching based on this. From the above description, the structure required to construct such a system is obvious. In addition, this application does not target any specific programming language. It should be understood that various programming languages can be used to implement the content of the present application described herein, and the description of the specific language above is to disclose the best embodiment of the present application.

The specification provided here explains a lot of specific details. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this description.

Similarly, it should be understood that in order to streamline the disclosure and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present application, various features of the present application are sometimes grouped together into a single embodiment, Figure, or its description. However, the disclosed method should not be interpreted as reflecting the intention that the claimed application claims more features than those explicitly recited in each claim. Rather, as the claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Therefore, the claims following a specific embodiment are hereby expressly incorporated into the specific embodiment, where each claim itself serves as a separate embodiment of the present application.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and set in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition, they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and/or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstract and drawings) and any method so disclosed may be adopted in any combination All processes or units of equipment are combined. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose.

In addition, those skilled in the art can understand that although some of the embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments is meant to be within the scope of the present application And form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

Each component embodiment of the present application may be implemented by hardware, or implemented by a software module running on one or more processors, or implemented by a combination thereof. Those skilled in the art should understand that, in practice, a microprocessor or a digital signal processor (DSP) may be used to implement some or all functions of some or all components in a natural semantic understanding device according to an embodiment of the present application. The present application may also be implemented as a device or device program (eg, computer program and computer program product) for performing part or all of the method described herein. Such a program implementing the present application may be stored on a computer-readable medium, or may have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form. It should be noted that the above-mentioned embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs between parentheses should not be constructed as limitations on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "one" before an element does not exclude the presence of multiple such elements. The application can be realized by means of hardware including several different elements and by means of a suitably programmed computer. In the unit claims enumerating several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third does not indicate any order. These words can be interpreted as names.

Claims

A method of natural semantic understanding, which includes:

Receive question statements sent by smart terminals;

Use a preset word segmentation algorithm to split the question sentence into multiple words;

Searching for sentences containing at least one of the words in the preset question and answer library;

Calculating the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value;

The response corresponding to the sentence with the highest similarity is selected and sent to the smart terminal.
The method according to claim 1, wherein the method further comprises:

Determine whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold;

If the similarity value corresponding to the sentence with the highest similarity is less than the preset first threshold, the confidence index is reduced by the preset first value;

If the similarity value corresponding to the sentence with the highest similarity is not less than a preset first threshold, determine whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold;

If the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the preset second threshold, increase the confidence index by the preset second value;

Determine whether the confidence index is less than a preset third threshold;

If the confidence index is less than the preset third threshold, a manual intervention algorithm is triggered.
The method according to claim 2, wherein the manual intervention algorithm includes:

Search for answers to question statements sent by the smart terminal;

When the answer to the question sentence is searched, the question sentence and the answer to the question sentence are stored in the preset question and answer library.
The method according to claim 2, characterized in that

If the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold, the response corresponding to the sentence with the highest similarity is sent to the smart terminal in a preset warning manner.
A natural semantic understanding device, characterized by including:

Receiving module: used to receive the question statement sent by the intelligent terminal;

Splitting module: used to split the question sentence into multiple words using a preset word segmentation algorithm;

Search module: used to search for a sentence containing at least one of the words in the preset question and answer library;

Calculation module: used to calculate the similarity between the sentence and the question sentence sent by the smart terminal to obtain a similarity value;

Sending module: used to select the reply corresponding to the sentence with the highest similarity to send to the smart terminal.
The device according to claim 5, wherein the device further comprises:

A first judgment module: used to judge whether the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold;

A first calculation module: used to reduce the confidence index by a preset first value when the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold;

Second judgment module: used to determine whether the similarity value corresponding to the sentence with the highest similarity is greater than or equal to the preset second when the similarity value corresponding to the sentence with the highest similarity is not less than the preset first threshold Threshold

A second calculation module: used to increase the confidence index by a preset second value when the similarity value corresponding to the sentence with the highest similarity is greater than or equal to a preset second threshold;

The third judgment module: used to judge whether the confidence index is less than a preset third threshold;

Trigger module: used to trigger a manual intervention algorithm when the confidence index is less than a preset third threshold.
The device according to claim 6, wherein the manual intervention algorithm includes:

Search for answers to question statements sent by the smart terminal;

When the answer to the question sentence is searched, the question sentence and the answer to the question sentence are stored in the preset question and answer library.
The apparatus according to claim 6, wherein if the judgment result of the first judgment module is that the similarity value corresponding to the sentence with the highest similarity is less than a preset first threshold, the sentence with the highest similarity is selected The corresponding reply is sent to the smart terminal in a preset warning manner.
A computing device includes: a processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface communicate with each other through the communication bus; the memory is used to store at least one Executing instructions, the executable instructions causing the processor to perform operations corresponding to a method for natural semantic understanding according to any one of claims 1-4.
A computer-readable storage medium storing at least one execution instruction in the storage medium, the executable instruction causing a processor to perform a natural semantic understanding method according to any one of claims 1-4 Operation.