CN111401011B - Information processing method and device and electronic equipment - Google Patents
Information processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111401011B CN111401011B CN201811614184.5A CN201811614184A CN111401011B CN 111401011 B CN111401011 B CN 111401011B CN 201811614184 A CN201811614184 A CN 201811614184A CN 111401011 B CN111401011 B CN 111401011B
- Authority
- CN
- China
- Prior art keywords
- similarity
- input information
- display information
- information
- common word
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 41
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 103
- 238000000034 method Methods 0.000 claims abstract description 26
- 230000004044 response Effects 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 4
- 230000002860 competitive effect Effects 0.000 description 36
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides an information processing method, an information processing device and electronic equipment, wherein the method comprises the following steps: firstly, acquiring input information; display information in a screen of the intelligent equipment at the moment of receiving the input information is obtained; then, according to the display information, carrying out semantic analysis on the input information; and then controlling the intelligent equipment to output response information corresponding to the input information according to the result of semantic analysis. The information processing method, the information processing device and the electronic equipment provided by the embodiment of the invention improve the accuracy of the output content corresponding to the input information.
Description
Technical Field
The embodiment of the invention relates to the technical field of electronic equipment, in particular to an information processing method and device and electronic equipment.
Background
With the rapid development of electronic devices, application of information recognition systems to electronic devices is becoming more and more popular. For example, speech information recognition or handwriting information recognition, etc. Taking voice information recognition as an example, when a user dials a call while driving a vehicle or inputs a destination while using car navigation, a mobile phone or car navigation is generally controlled in a voice manner, so that after receiving voice information input by the user, the mobile phone or car navigation recognizes the voice information, thereby executing a corresponding operation.
In the prior art, when identifying voice information for a mobile phone or a car navigation, the voice information input by a user needs to be converted into text information, but during the conversion process, a "fine movie" may be identified as a "competitive product point map", so that when searching an output result corresponding to the fine movie by an edit distance algorithm, the character string distance between the "competitive product point map" and the "fine movie" is larger, and therefore, the output result corresponding to the voice information cannot be found accurately.
Disclosure of Invention
The embodiment of the invention provides an information processing method, an information processing device and electronic equipment, which are used for improving the accuracy of output content corresponding to input information.
In a first aspect, an embodiment of the present invention provides an information processing method, which may include:
acquiring input information;
acquiring display information in a screen of the intelligent equipment at the input information receiving moment;
according to the display information, carrying out semantic analysis on the input information;
and controlling the intelligent equipment to output response information corresponding to the input information according to the result of semantic analysis.
In one possible implementation manner, the semantic parsing of the input information according to the display information includes:
Determining a common word corresponding to display information according to a mapping relation between the display information and the common word;
and if any common word is included in the input information, carrying out semantic analysis on the input information according to the display information corresponding to the common word.
In one possible implementation manner, the performing semantic parsing on the input information according to the display information corresponding to the common word includes:
deleting the common words contained in the input information to obtain target input information;
and carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
In one possible implementation manner, the performing semantic parsing on the input information according to the display information corresponding to the common word includes:
calculating a first similarity between the input information and each piece of display information corresponding to the common word;
and determining a semantic analysis result corresponding to the input information according to the first similarity.
In one possible implementation manner, the performing semantic parsing on the target input information according to the display information corresponding to the common word includes:
calculating a second similarity between the target input information and each piece of display information corresponding to the common word;
And determining a semantic analysis result corresponding to the target input information according to the second similarity.
In one possible implementation manner, the performing semantic parsing on the input information according to the display information corresponding to the common word includes:
calculating a first similarity between the input information and each display information corresponding to the common word, and calculating a second similarity between the target input information and each display information corresponding to the common word;
determining target similarity according to the first similarity and the second similarity;
and determining a semantic analysis result corresponding to the input information according to the target similarity.
In one possible implementation, the first similarity includes at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
In one possible implementation manner, if the first similarity includes at least two types of similarities, the calculating the first similarity between the input information and each display information corresponding to the common word includes:
respectively calculating at least two types of similarity between the input information and each display information corresponding to the common words;
And determining the similarity with the largest value in the at least two types of similarity as the first similarity.
In one possible implementation, the second similarity includes at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
In one possible implementation manner, if the second similarity includes at least two types of similarities, the calculating the second similarity between the target input information and each display information corresponding to the common word includes:
respectively calculating at least two types of similarity between the target input information and each display information corresponding to the common word;
and determining the similarity with the largest value in the at least two types of similarity as the second similarity.
In a second aspect, embodiments of the present application further provide an information processing apparatus, which may include:
an acquisition unit configured to acquire input information; acquiring display information in a screen of the intelligent equipment at the input information receiving moment;
the analysis unit is used for carrying out semantic analysis on the input information according to the display information;
and the output unit is used for controlling the intelligent equipment to output response information corresponding to the input information according to the result of semantic analysis.
In one possible implementation manner, the parsing unit is specifically configured to determine, according to a mapping relationship between display information and a common word, the common word corresponding to the display information; and if any common word is included in the input information, carrying out semantic analysis on the input information according to the display information corresponding to the common word.
In one possible implementation manner, the parsing unit is specifically configured to delete the common words included in the input information to obtain target input information; and carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
In one possible implementation manner, the parsing unit is specifically configured to calculate a first similarity between the input information and each display information corresponding to the common word; and determining a semantic analysis result corresponding to the input information according to the first similarity.
In a possible implementation manner, the parsing unit is specifically configured to calculate a second similarity between the target input information and each display information corresponding to the common word; and determining a semantic analysis result corresponding to the target input information according to the second similarity.
In one possible implementation manner, the parsing unit is specifically configured to calculate a first similarity between the input information and each display information corresponding to the common word, and calculate a second similarity between the target input information and each display information corresponding to the common word; determining target similarity according to the first similarity and the second similarity; and determining a semantic analysis result corresponding to the input information according to the target similarity.
In one possible implementation, the first similarity includes at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
In one possible implementation manner, if the first similarity includes at least two types of similarities, the parsing unit is specifically configured to calculate at least two types of similarities between the input information and each display information corresponding to the common word, respectively; and determining the similarity with the largest value in the at least two types of similarity as the first similarity.
In one possible implementation, the second similarity includes at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
In one possible implementation manner, if the second similarity includes at least two types of similarities, the parsing unit is specifically configured to calculate at least two types of similarities between the target input information and each display information corresponding to the common word, respectively; and determining the similarity with the largest value in the at least two types of similarity as the second similarity.
In a third aspect, embodiments of the present invention also provide an electronic device that may include a processor and a memory, wherein,
the memory is used for storing program instructions;
the processor is configured to read the program instructions in the memory, and execute the information processing method according to any one of the above first aspects according to the program instructions in the memory.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium, characterized in that,
a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the information processing method according to any one of the above first aspects.
The information processing method, the information processing device and the electronic equipment provided by the embodiment of the invention acquire input information firstly; display information in a screen of the intelligent equipment at the moment of receiving the input information is obtained; then, according to the display information, carrying out semantic analysis on the input information; and then, according to the result of semantic analysis, controlling the intelligent equipment to output response information corresponding to the input information. Therefore, when the information processing method, the information processing device and the electronic equipment provided by the embodiment of the invention output the content corresponding to the input information, the content corresponding to the input information is not determined simply according to the input information after semantic analysis, but is determined by combining the display information in the screen of the intelligent equipment at the moment of receiving the input information, so that the accuracy of the output content corresponding to the input information is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of an information processing method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of semantic analysis of input information according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another semantic parsing of input information according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present 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.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, when voice information is identified for a mobile phone or a vehicle navigation, the voice information input by a user needs to be converted into text information, but in the conversion process, the accuracy of information identification is lower due to inaccurate conversion. In order to improve accuracy of information identification, the embodiment of the invention provides an information processing method, which comprises the steps of firstly acquiring input information; display information in a screen of the intelligent equipment at the moment of receiving the input information is obtained; then, according to the display information, carrying out semantic analysis on the input information; and then, according to the result of semantic analysis, controlling the intelligent equipment to output response information corresponding to the input information. Therefore, in the information processing method provided by the embodiment of the invention, when the content corresponding to the input information is output, the content corresponding to the input information is not determined simply according to the input information after semantic analysis, but is determined by combining the display information in the screen of the intelligent equipment at the receiving moment of the input information, so that the accuracy of the output content corresponding to the input information is improved.
The following describes the technical scheme of the present invention and how the technical scheme of the present invention solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes will not be described in detail in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of an information processing method according to an embodiment of the present invention, where the method may be executed by a server or may be executed by a controller of an intelligent device. For example, referring to fig. 1, the information processing method may include:
s101, acquiring input information.
The input information may be voice information or text information. For example, when the voice information is "i want to watch a fine movie", the input information "i want to watch a fine movie" may be recognized as "i want to watch a competitive point play" and "i want to watch a competitive point play" may be understood as the input information in the process of performing voice recognition on the voice information. When the input information is text information, the "i want to watch the top-quality movie" may be input as "i want to watch the competitive product bitmap" due to the editing error, and similarly, the "i want to watch the competitive product bitmap" may be understood as the input information.
Optionally, when acquiring the input information, the microphone of the electronic device may collect the input information of the user, or may receive the input information of the user by means of a network or bluetooth, or the like, and of course, the screen of the electronic device may also acquire the input information of the user.
S102, acquiring display information in a screen of the intelligent device at the time of receiving the input information.
The display information in the screen of the smart device may include a fine movie, a best quality galloping, information in a user, a menu, etc., which is only taken herein as an example for illustration, but the embodiment of the present invention is not limited thereto.
In this embodiment of the present application, the time of receiving the input information is not limited to an instant of receiving the input information, but is understood to be a current time period of receiving the input information, which may be set according to actual needs, and the embodiment of the present application is not limited specifically herein.
After the display information in the screen of the intelligent device at the time of receiving the input information is acquired through S102, in order to accurately perform semantic analysis on the input information, thereby improving the accuracy of the output result corresponding to the input information, therefore, when performing semantic analysis on the input information, the following S103 may be performed:
s103, carrying out semantic analysis on the input information according to the display information.
When the input information is voice information, automatic voice recognition technology (Automatic Speech Recognition, abbreviated as ASR) technology can be adopted to recognize the voice information when the input information is subjected to semantic analysis, so that recognized input information is obtained, and the recognized input information is text information. When the input information is text information, the semantic analysis can be directly performed on the input information. When the input information is subjected to semantic analysis, the result of the semantic analysis may be inaccurate, so that the input information can be subjected to semantic analysis by combining the display information.
For example, when the input information is "i want to watch the bid item point map", at this time, if the output result corresponding to the "i want to watch the bid item point map" is only used, the accuracy of the output result is not high, and the intention of the user cannot be correctly understood, so that the semantic analysis can be performed on the input information "i want to watch the bid item point map" by combining the display information "fine movie", "best-quality galloping", "user center" and "menu" in the screen of the intelligent device at the time of receiving the input information of the electronic device, so that the input information "i want to watch the fine movie" can be correctly analyzed. By way of example, the input information and the display information may be as follows:
After the input information is semantically parsed according to the display information in S103, a result of the semantic parsing corresponding to the input information may be obtained, and then, according to the result of the semantic parsing, an output result corresponding to the input information is determined, that is, the following S104 is executed:
s104, controlling the intelligent equipment to output response information corresponding to the input information according to the result of semantic analysis.
For example, when the result of the semantic analysis is "i want to watch the fine movie", various fine movies may be displayed to the user according to the result of the semantic analysis, and when the result of the semantic analysis is "input error", prompt information, such as "input error, please re-input", may be output to the user according to the result of the semantic analysis.
After the input information is semantically parsed according to the display information through S103, the intelligent device can be controlled to output the response information corresponding to the input information according to the result of the semantically parsed.
The information processing method provided by the embodiment of the invention comprises the steps of firstly acquiring input information; display information in a screen of the intelligent equipment at the moment of receiving the input information is obtained; then, according to the display information, carrying out semantic analysis on the input information; and then, according to the result of semantic analysis, controlling the intelligent equipment to output response information corresponding to the input information. Therefore, in the information processing method provided by the embodiment of the invention, when the content corresponding to the input information is output, the content corresponding to the input information is not determined simply according to the input information after semantic analysis, but is determined by combining the display information in the screen of the intelligent equipment at the receiving moment of the input information, so that the accuracy of the output content corresponding to the input information is improved.
Based on the embodiment shown in fig. 1, in the embodiment of the present invention, when S103 performs semantic parsing on input information according to display information, the semantic parsing may be implemented in at least two possible ways, and the two possible ways will be described in detail below.
In a first possible implementation manner, when performing semantic analysis on input information according to display information, for example, please refer to fig. 2, fig. 2 is a schematic diagram of performing semantic analysis on input information according to an embodiment of the present invention, and the method may include:
S201, determining the common words corresponding to the display information according to the mapping relation between the display information and the common words.
In general words, the term "usual words" may be understood as defined words commonly used before information is displayed in general sentences including information displayed, and may be words for representing the intention of a user operation.
In practice, each different type of displayed information may correspond to the same set of common words, e.g., "top-quality movie," "best-quality fly" (movie name), "television show," "popular television show," "me love me" (drama name), etc., may correspond to the same set of common words, which may include "i want to see," "look at," "see," etc.
In addition, the same display information may correspond to different types of common words, for example, the display information "top-quality movie" may correspond to the common words "i want to see", "open". Different types of display information may also correspond to the same general word, for example, display information "top-quality movie" and display information "best quality galloping" may correspond to the same general word "open".
In the embodiment of the application, the mapping relation between the display information and the common words can be pre-established, so that after the display information in the screen of the intelligent device at the input information receiving moment is acquired, the common words corresponding to the display information can be determined. It should be noted that, in the embodiment of the present application, instead of establishing a mapping relationship between display information and a common word in advance before executing the common word corresponding to the determined display information each time, the mapping relationship between display information and the common word may be established before executing the common word corresponding to the determined display information for the first time. Of course, if new display information or new common words are generated, the mapping relationship between the display information and the common words may be updated.
For example, when the display information is "fine movie", "movie" and "best quality driving", the corresponding common words may be "i want to see", "i want not to see", etc., and when the display information is "user center" and "menu", the corresponding common words may be "on", "off", and for example, see the following:
after determining the common words corresponding to the display information according to the mapping relationship between the display information and the common words in S201, it may be further determined whether any common word corresponding to the display information is included in the input information.
S202, if any common word is included in the input information, semantic analysis is carried out on the input information according to the display information corresponding to the common word.
Optionally, when semantic analysis is performed on the input information according to the display information corresponding to the common word, first similarity between the input information and each display information corresponding to the common word may be calculated; and determining a semantic analysis result corresponding to the input information according to the first similarity.
It should be noted that, the first similarity includes at least one of the following: editing similarity, semantic similarity, pinyin similarity, and character similarity, although the embodiment of the present application is described only by taking the first similarity including at least one of four types of similarity as an example, and the embodiment of the present application is not limited thereto.
The first similarity comprises at least one of: editing similarity, semantic similarity, pinyin similarity and character similarity, in other words, only one of editing similarity, semantic similarity, pinyin similarity or character similarity between the input information and each display information corresponding to the common word can be calculated, the similarity is the first similarity, and the semantic analysis result corresponding to the input information is determined according to the first similarity; of course, a plurality of (i.e., two or more) similarities among the edit similarity, the semantic similarity, the pinyin similarity or the character similarity between the input information and each display information corresponding to the common word can be calculated respectively, and a semantic analysis result corresponding to the input information can be determined according to the calculated plurality of similarities.
It should be noted that, if the first similarity includes at least two types of similarity, when determining a result of semantic analysis corresponding to the input information according to two or more of editing similarity, semantic similarity, pinyin similarity, or character similarity, at least two types of similarity between the input information and each display information corresponding to the common word are calculated respectively; and determining the similarity with the maximum value in at least two types of similarity as a first similarity, and further determining a semantic analysis result corresponding to the input information according to the first similarity.
Taking input information as "i want to watch a competitive product point map" as an example, the input information includes a common word "i want to watch", display information corresponding to the common word "i want to watch" is "fine movie", "movie" and "best quality galloping", and then a first similarity between the input information "i want to watch a competitive product point map" and each display information corresponding to the common word "i want to watch" in "fine movie", "movie" and "best quality galloping" can be calculated respectively, and semantic analysis is performed on the input information "i want to watch a fine movie" according to the first similarity, and as an example, please see the following table 1:
TABLE 1
| Inputting information | Display information in smart device screen | Similarity degree |
| I want to see the bid amount point | Top-quality film | 1 |
| I want to see the bid amount point | Film making apparatus | 0.53 |
| I want to see the bid amount point | High-grade flying car | 0.4 |
As can be seen by combining table 1, the similarity between the input information "i want to watch the competitive product bitmap" and the display information "fine movie" is 1, the similarity between the input information "i want to watch the competitive product bitmap" and the display information "movie" is 0.53, and the similarity between the input information "i want to watch the competitive product bitmap" and the display information "best-quality driving" is 0.4, it can be seen that the similarity between the input information "i want to watch the competitive product bitmap" and the display information "fine movie" is the highest, then semantic analysis can be performed on the input information "i want to watch the competitive product bitmap" according to the display information "fine movie" corresponding to the similarity, so that the semantic analysis result "i want to watch the fine movie" corresponding to the input information "i want to watch the competitive product bitmap" is obtained, the accuracy of the analysis result corresponding to the input information is improved, and the accuracy of the output content corresponding to the input information "i want to watch the fine movie" is improved when the output result is determined according to the analysis result.
In addition, in this possible implementation manner, when calculating the similarity between the input information including the common word and the display information, the common word included in the input information may be added before each display information, and then the first similarity between the input information including the common word and each display information after adding the common word may be calculated.
Taking input information as an example of 'I want to watch a competitive product point map', wherein the input information comprises common words of 'I want to watch', display information is 'fine movie', 'movie' and 'best quality flying', common words of 'I want to watch' are respectively added before the display information is 'fine movie', 'movie' and 'best quality flying', the added display information is 'I want to watch fine movie', 'I want to watch movie' and 'I want to watch best quality flying', and the first similarity between the input information is 'I want to watch a competitive product point map' and each display information in the added display information is 'I want to watch fine movie', 'I want to watch movie' and 'I want to watch best quality flying' is calculated; and according to the first similarity, carrying out semantic analysis on the input information 'I want to see the bid item point map'. For example, please refer to the following table 2:
TABLE 2
As can be seen by combining table 2, the similarity between the input information "i want to watch the competitive product bitmap" and the added display information "i want to watch the competitive product movie" is 1, the similarity between the input information "i want to watch the competitive product bitmap" and the added display information "i want to watch the movie" is 0.53, the similarity between the input information "i want to watch the competitive product bitmap" and the added display information "i want to watch the competitive product galloping" is 0.4, it can be seen that the similarity between the input information "i want to watch the competitive product bitmap" and the added display information "i want to watch the competitive product movie" is the highest, and the resolution of the input information "i want to watch the competitive product bitmap" can be performed according to the added display information corresponding to the similarity, so that the resolution of the input information "i want to watch the competitive product bitmap" corresponding to the semantic resolution "i want to watch the competitive product movie" is improved, and the resolution of the output content corresponding to the input information "i want to watch the competitive product movie" is improved when the output result is determined according to the resolution result.
In a second possible implementation manner, when performing semantic analysis on input information according to display information, for example, please refer to fig. 3, fig. 3 is another schematic diagram of performing semantic analysis on input information according to another embodiment of the present invention, the method may include:
S301, determining the common words corresponding to the display information according to the mapping relation between the display information and the common words.
It should be noted that, the description in S301 may refer to the description in S201, and here, the embodiment of the present application will not be described in detail.
S302, if the input information comprises any common word, deleting the common word contained in the input information to obtain target input information.
In the embodiment of the present invention, unlike S202, in S202, the input information is subjected to semantic analysis directly from the display information corresponding to the common word. In this step S302, in order to improve the matching efficiency, the common words included in the input information may be deleted to obtain the target input information before the input information is semantically parsed based on the display information corresponding to the common words.
By way of example, taking the input information "i want to see the bid item bitmap" as an example, the input information "i want to see the bid item bitmap" includes the common word "i want to see" and, in order to improve the matching efficiency, the common word "i want to see" in the input information "i want to see the bid item bitmap" may be deleted, so as to obtain the deleted target input information "bid item bitmap".
After the deletion processing of the input information according to the common words, the following S202 may be performed:
s303, carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
Optionally, when semantic analysis is performed on the target input information according to the display information corresponding to the common word, a second similarity between the target input information and each display information corresponding to the common word may be calculated first; and determining a semantic analysis result corresponding to the target input information according to the second similarity.
The second similarity includes at least one of the following: editing similarity, semantic similarity, pinyin similarity, and character similarity, although the embodiments of the present application are described by taking the second similarity including at least one of the four types of similarity as an example, and are not intended to be limiting.
The second similarity includes at least one of: editing similarity, semantic similarity, pinyin similarity and character similarity, in other words, only one of editing similarity, semantic similarity, pinyin similarity or character similarity between the target input information and each display information corresponding to the common word can be calculated, the similarity is the second similarity, and the result of semantic analysis corresponding to the target input information is determined according to the second similarity; of course, two or more similarities among the edit similarity, the semantic similarity, the pinyin similarity or the character similarity between the target input information and each display information corresponding to the common word can be calculated respectively, and the result of semantic analysis corresponding to the target input information can be determined according to the two or more similarities among the edit similarity, the semantic similarity, the pinyin similarity or the character similarity.
It should be noted that, if the second similarity includes at least two types of similarity, when determining a result of semantic analysis corresponding to the target input information according to two or more of the edit similarity, the semantic similarity, the pinyin similarity, and the character similarity, at least two types of similarity between the target input information and each display information corresponding to the common word are calculated respectively; and determining the similarity with the maximum value in at least two types of similarity as a second similarity, and further determining a semantic analysis result corresponding to the target input information according to the second similarity.
Taking the deleted target input information as "competitive product point map" as an example, the corresponding display information may be "fine movie", "movie" and "premium galloping", and then the second similarity between the target input information "fine movie" and each display information of the display information "fine movie", "movie" and "premium galloping" corresponding to the common word "i want to watch" may be calculated respectively, and the semantic analysis is performed on the target input information "competitive product point map" according to the second similarity, for example, please refer to the following table 3:
TABLE 3 Table 3
| Target input information | Display information in smart device screen | Similarity degree |
| Bidding point map | Top-quality film | 1 |
| Bidding point map | Film making apparatus | 0.53 |
| Bidding point map | High-grade flying car | 0.4 |
As can be seen from table 3, the similarity between the target input information "competitive product point map" and the display information "fine movie" is 1, the similarity between the target input information "competitive product point map" and the display information "movie" is 0.53, and the similarity between the target input information "competitive product point map" and the display information "fine movie" is 0.4, so that it can be seen that the similarity between the target input information "competitive product point map" and the display information "fine movie" is the highest, and the semantic analysis can be performed on the target input information "competitive product point map" according to the display information "fine movie" corresponding to the similarity, so that the result "fine movie" of the semantic analysis corresponding to the target input information "competitive product point map" is obtained, the accuracy of the analysis result corresponding to the target input information is improved, and the accuracy of the output content corresponding to the target input information "competitive product point map" is improved when the output result is determined according to the analysis result.
In addition, it should be noted that, in the embodiment of the present application, when the input information is semantically parsed according to the display information corresponding to the common word, a first similarity between the input information and each display information corresponding to the common word and a second similarity between the target input information and each display information corresponding to the common word may be calculated respectively; determining target similarity according to the first similarity and the second similarity; and then, determining a semantic analysis result corresponding to the input information according to the target similarity. In this implementation manner, the method for calculating the first similarity and the second similarity is the same as the method for separately calculating the first similarity and the second similarity, which is not described in detail herein.
It should be noted that, when the semantic analysis is performed on the input information according to the display information, the two possible implementation manners may be directly executed, or before the two possible implementation manners are executed, the absolute similarity between the input information and the display information may be calculated, and the semantic analysis is performed on the input information according to the absolute similarity. If the input information and the display information are identical, the absolute similarity between the input information and the display information is considered to be 1; if the input information and the display information have one word or a plurality of words which are different, the absolute similarity between the input information and the display information is considered to be 0. The method comprises the following steps: if the absolute similarity between the input information and the display information is 0, the input information and the display information are not matched, and the possible implementation modes need to be continuously executed at the moment so as to carry out semantic analysis on the input information through the possible implementation modes; in contrast, if the absolute similarity between the input information and the display information is 1, the absolute matching between the input information and the display information is described, and at this time, the semantic analysis result corresponding to the input information can be directly determined without executing the possible implementation manners described above.
Fig. 4 is a schematic structural diagram of an information processing apparatus 40 according to an embodiment of the present invention, and as shown in fig. 4, for example, the information processing apparatus 40 may include:
an acquisition unit 401 for acquiring input information; and acquiring display information in the screen of the intelligent device at the time of receiving the input information.
The parsing unit 402 is configured to perform semantic parsing on the input information according to the display information.
And the output unit 403 is configured to control the intelligent device to output response information corresponding to the input information according to the result of the semantic analysis.
Optionally, the parsing unit 402 is specifically configured to determine a common word corresponding to the display information according to a mapping relationship between the display information and the common word; if the input information comprises any common word, carrying out semantic analysis on the input information according to the display information corresponding to the common word.
Optionally, the parsing unit 402 is specifically configured to delete a common word included in the input information to obtain target input information; and carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
Optionally, the parsing unit 402 is specifically configured to calculate a first similarity between the input information and each display information corresponding to the common word; and determining a semantic analysis result corresponding to the input information according to the first similarity.
Optionally, the parsing unit 402 is specifically configured to calculate a second similarity between the target input information and each display information corresponding to the common word; and determining a semantic analysis result corresponding to the target input information according to the second similarity.
Optionally, the parsing unit 402 is specifically configured to calculate a first similarity between the input information and each display information corresponding to the common word, and calculate a second similarity between the target input information and each display information corresponding to the common word; determining target similarity according to the first similarity and the second similarity; and determining a semantic analysis result corresponding to the input information according to the target similarity.
Optionally, the first similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
Optionally, if the first similarity includes at least two types of similarity, the parsing unit 402 is specifically configured to calculate at least two types of similarity between the input information and each display information corresponding to the common word; and determining the similarity with the largest value in the at least two types of similarity as the first similarity.
Optionally, the second similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
Optionally, if the second similarity includes at least two types of similarity, the parsing unit 402 is specifically configured to calculate at least two types of similarity between the target input information and each display information corresponding to the common word; and determining the similarity with the largest value among the at least two types of similarity as the second similarity.
The information processing apparatus 40 according to the embodiment of the present invention may execute the technical scheme of the information processing method according to any of the foregoing embodiments, and the implementation principle and the beneficial effects of the information processing method are similar to those of the information processing method, and will not be described herein.
Fig. 5 is a schematic structural diagram of an electronic device 50 according to an embodiment of the present invention, referring to fig. 5, the electronic device 50 may include a processor 501 and a memory 502, where,
the memory 502 is used to store program messages.
The processor 501 is configured to read the program message in the memory 502 and execute the information processing method according to any one of the embodiments described above according to the program message in the memory 502.
The electronic device 50 may specifically be an intelligent device itself; the electronic device may specifically be an external device that communicates with the intelligent device, such as a server; the present invention is not particularly limited thereto.
The electronic device 50 in the embodiment of the present invention may execute the technical scheme of the information processing method in any of the foregoing embodiments, and the implementation principle and the beneficial effects of the information processing method are similar to those of the implementation principle and the beneficial effects of the information processing method, and are not described herein again.
The embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, where when the computer program is executed by a processor, the technical solution of the information processing method shown in any of the foregoing embodiments may be executed, and the implementation principle and the beneficial effects of the information processing method are similar, and are not repeated herein.
The processor in the above embodiments may be a general purpose processor, a digital signal processor (digital signal processor, DSP), an application specific integrated circuit (application specific integrated circuit, ASIC), an off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a memory medium well known in the art such as random access memory (random access memory, RAM), flash memory, read-only memory (ROM), programmable read-only memory, or electrically erasable programmable memory, registers, and the like. The storage medium is located in a memory, and the processor reads instructions from the memory and, in combination with its hardware, performs the steps of the method described above.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (18)
1. An information processing method, characterized by comprising:
acquiring input information;
acquiring display information in a screen of the intelligent equipment at the input information receiving moment;
according to the display information, carrying out semantic analysis on the input information;
according to the result of semantic analysis, controlling the intelligent equipment to output response information corresponding to the input information;
The semantic analysis of the input information according to the display information comprises the following steps:
determining a common word corresponding to display information according to a mapping relation between the display information and the common word;
if the input information comprises any common word, carrying out semantic analysis on the input information according to display information corresponding to the common word; or deleting the common words contained in the input information to obtain target input information, and carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
2. The method according to claim 1, wherein the semantic parsing of the input information according to the display information corresponding to the common word includes:
calculating a first similarity between the input information and each piece of display information corresponding to the common word;
and determining a semantic analysis result corresponding to the input information according to the first similarity.
3. The method according to claim 1, wherein the semantic parsing of the target input information according to the display information corresponding to the common word includes:
Calculating a second similarity between the target input information and each piece of display information corresponding to the common word;
and determining a semantic analysis result corresponding to the target input information according to the second similarity.
4. The method according to claim 1, wherein the semantic parsing of the input information according to the display information corresponding to the common word includes:
deleting the common words contained in the input information to obtain target input information;
calculating a first similarity between the input information and each display information corresponding to the common word, and calculating a second similarity between the target input information and each display information corresponding to the common word;
determining target similarity according to the first similarity and the second similarity;
and determining a semantic analysis result corresponding to the input information according to the target similarity.
5. The method of claim 2 or 4, wherein the first similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
6. The method of claim 5, wherein if the first similarity includes at least two types of similarity, the calculating the first similarity between the input information and each display information corresponding to the common word includes:
Respectively calculating at least two types of similarity between the input information and each display information corresponding to the common words;
and determining the similarity with the largest value in the at least two types of similarity as the first similarity.
7. The method of claim 3 or 4, wherein the second similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
8. The method of claim 7, wherein if the second similarity includes at least two types of similarities, the calculating the second similarity between the target input information and each display information corresponding to the common word includes:
respectively calculating at least two types of similarity between the target input information and each display information corresponding to the common word;
and determining the similarity with the largest value in the at least two types of similarity as the second similarity.
9. An information processing apparatus, characterized by comprising:
an acquisition unit configured to acquire input information; acquiring display information in a screen of the intelligent equipment at the input information receiving moment;
The analysis unit is used for carrying out semantic analysis on the input information according to the display information;
the output unit is used for controlling the intelligent equipment to output response information corresponding to the input information according to the result of semantic analysis;
the analysis unit is specifically used for determining the common words corresponding to the display information according to the mapping relation between the display information and the common words; if the input information comprises any common word, carrying out semantic analysis on the input information according to display information corresponding to the common word; or deleting the common words contained in the input information to obtain target input information, and carrying out semantic analysis on the target input information according to the display information corresponding to the common words.
10. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
the analysis unit is specifically configured to calculate a first similarity between the input information and each display information corresponding to the common word; and determining a semantic analysis result corresponding to the input information according to the first similarity.
11. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
the analysis unit is specifically used for calculating a second similarity between the target input information and each piece of display information corresponding to the common word; and determining a semantic analysis result corresponding to the target input information according to the second similarity.
12. The apparatus of claim 9, wherein the device comprises a plurality of sensors,
the analyzing unit is specifically configured to delete the common words included in the input information to obtain target input information; calculating a first similarity between the input information and each display information corresponding to the common word, and calculating a second similarity between the target input information and each display information corresponding to the common word; determining target similarity according to the first similarity and the second similarity; and determining a semantic analysis result corresponding to the input information according to the target similarity.
13. The apparatus of claim 10 or 12, wherein the first similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
14. The apparatus of claim 13, wherein if the first degree of similarity comprises at least two types of degrees of similarity,
the analysis unit is specifically configured to calculate at least two types of similarity between the input information and each display information corresponding to the common word; and determining the similarity with the largest value in the at least two types of similarity as the first similarity.
15. The apparatus of claim 11 or 12, wherein the second degree of similarity comprises at least one of: edit similarity, semantic similarity, pinyin similarity, and character similarity.
16. The apparatus of claim 15, wherein if the second similarity comprises at least two types of similarity,
the analysis unit is specifically configured to calculate at least two types of similarity between the target input information and each display information corresponding to the common word; and determining the similarity with the largest value in the at least two types of similarity as the second similarity.
17. An electronic device comprising a processor and a memory, wherein,
the memory is used for storing program instructions;
the processor is configured to read the program instructions in the memory and execute the information processing method according to any one of claims 1 to 8 according to the program instructions in the memory.
18. A computer-readable storage medium comprising,
a computer program stored on a computer readable storage medium, which when executed by a processor performs the information processing method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614184.5A CN111401011B (en) | 2018-12-27 | 2018-12-27 | Information processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811614184.5A CN111401011B (en) | 2018-12-27 | 2018-12-27 | Information processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401011A CN111401011A (en) | 2020-07-10 |
| CN111401011B true CN111401011B (en) | 2024-01-30 |
Family
ID=71430123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811614184.5A Active CN111401011B (en) | 2018-12-27 | 2018-12-27 | Information processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401011B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893345A (en) * | 2016-03-28 | 2016-08-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN108766071A (en) * | 2018-04-28 | 2018-11-06 | 北京猎户星空科技有限公司 | A kind of method, apparatus, storage medium and the relevant device of content push and broadcasting |
| CN108806671A (en) * | 2018-05-29 | 2018-11-13 | 杭州认识科技有限公司 | Semantic analysis, device and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106557461B (en) * | 2016-10-31 | 2019-03-12 | 百度在线网络技术（北京）有限公司 | Semantic analyzing and processing method and device based on artificial intelligence |
-
2018
- 2018-12-27 CN CN201811614184.5A patent/CN111401011B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893345A (en) * | 2016-03-28 | 2016-08-24 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN108766071A (en) * | 2018-04-28 | 2018-11-06 | 北京猎户星空科技有限公司 | A kind of method, apparatus, storage medium and the relevant device of content push and broadcasting |
| CN108806671A (en) * | 2018-05-29 | 2018-11-13 | 杭州认识科技有限公司 | Semantic analysis, device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 张波 ; 向阳 ; 王坚 ; .一种基于语义可理解的信息过滤算法.电子与信息学报.2010,(第10期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401011A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110377716B (en) | Interaction method and device for conversation and computer readable storage medium | |
| US10332507B2 (en) | Method and device for waking up via speech based on artificial intelligence | |
| CN110069608B (en) | Voice interaction method, device, equipment and computer storage medium | |
| CN106534548B (en) | Voice error correction method and device | |
| CN110164435A (en) | Audio recognition method, device, equipment and computer readable storage medium | |
| CN110415679B (en) | Voice error correction method, device, equipment and storage medium | |
| US20170195737A1 (en) | Method for video search and electronic device | |
| CN108305618B (en) | Voice acquisition and search method, intelligent pen, search terminal and storage medium | |
| CN110610698B (en) | Voice labeling method and device | |
| EP3627498A1 (en) | Method and system, for generating speech recognition training data | |
| CN107564526B (en) | Processing method, apparatus and machine-readable medium | |
| CN112507706A (en) | Training method and device of knowledge pre-training model and electronic equipment | |
| CN116737908A (en) | Knowledge question-answering method, device, equipment and storage medium | |
| CN111508472A (en) | Language switching method and device and storage medium | |
| CN111126084B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN109190116B (en) | Semantic analysis method, system, electronic device and storage medium | |
| CN104090915B (en) | Method and device for updating user data | |
| WO2021098175A1 (en) | Method and apparatus for guiding speech packet recording function, device, and computer storage medium | |
| CN110929514B (en) | Text collation method, text collation apparatus, computer-readable storage medium, and electronic device | |
| CN115858776B (en) | Variant text classification recognition method, system, storage medium and electronic equipment | |
| CN111401011B (en) | Information processing method and device and electronic equipment | |
| CN109033082B (en) | Learning training method and device of semantic model and computer readable storage medium | |
| EP4254400A1 (en) | Method and device for determining user intent | |
| CN115905497A (en) | Method, device, electronic equipment and storage medium for determining reply sentence | |
| CN113360590B (en) | Method and device for updating interest point information, electronic equipment and storage medium |
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 |