CN110765342A - Information query method and device, storage medium and intelligent terminal - Google Patents
Information query method and device, storage medium and intelligent terminal Download PDFInfo
- Publication number
- CN110765342A CN110765342A CN201910869534.0A CN201910869534A CN110765342A CN 110765342 A CN110765342 A CN 110765342A CN 201910869534 A CN201910869534 A CN 201910869534A CN 110765342 A CN110765342 A CN 110765342A
- Authority
- CN
- China
- Prior art keywords
- query
- natural language
- entity
- entity name
- language query
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An information query method and device, a storage medium and an intelligent terminal are provided, and the information query method comprises the following steps: acquiring a natural language query sentence input by a user; determining an entity to be queried in a natural language query statement from a knowledge base; identifying a query intent of a natural language query statement; and determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation. According to the technical scheme, the user can be allowed to query the information in a natural language mode, and the accuracy and convenience of query are improved.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to an information query method and device, a storage medium and an intelligent terminal.
Background
For current customer-oriented virtual products, such as fund products and insurance products, the products are of a wide variety. For the same type of fund, there may be a large profit gap due to the difference of fund managers or fund companies, and it is difficult for the average user to select a comparison in the face of such a large number of funds.
In the prior art, the above-mentioned product-related information is usually obtained by a search engine, for example, inputting "huanhu 300 index fund" in the search engine.
However, the information queried by the query methods in the prior art is generally general and tedious, and the user usually has a definite intention to query, for example, the user may only want to see what stocks in the fund taken place are, or see how the historical performance of the fund manager in a fund is, and it is difficult for the search engine in the prior art to query in one step, and it is necessary to perform a second filtering of the information after the first query to obtain effective information.
Disclosure of Invention
The technical problem solved by the invention is how to improve the accuracy and convenience of inquiry.
In order to solve the above technical problem, an embodiment of the present invention provides an information query method, where the information query method includes: acquiring a natural language query sentence input by a user; determining an entity to be queried in the natural language query statement from a knowledge base, wherein the entity to be queried comprises a query entity name; identifying a query intent of the natural language query statement; and determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation.
Optionally, the determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relationship includes: matching the query entity name with entity names in a plurality of preset mapping relations; if the entity name in the preset mapping relation is matched with the query entity name, matching the intention in the matched preset mapping relation with the query intention; and if the intention in the matched preset mapping relation is matched with the query intention, taking the answer in the matched preset mapping relation as the answer corresponding to the natural language query statement.
Optionally, the step of using the answer in the matched preset mapping relationship as the answer corresponding to the natural language query statement includes: directly taking an answer corresponding to the combination of the entity name and the intention in the matched preset mapping relation as an answer corresponding to the natural language query statement; or determining a query instruction corresponding to the combination of the entity name and the intention in the matched preset mapping relation, and taking an answer obtained by executing the query instruction as an answer corresponding to the natural language query statement.
Optionally, the determining, from the knowledge base, an entity to be queried in the natural language query statement includes: and sequencing the entity list in the knowledge base according to the natural language query statement input by the user, and taking the entity with the top sequence as the entity to be queried.
Optionally, the following algorithm is used to rank the entity list in the knowledge base: a learning-to-rank model, or syntactic analysis.
Optionally, the identifying the query intent of the natural language query statement includes: and sequencing the limited intention set corresponding to the entity to be queried according to the entity to be queried and the natural language query statement.
Optionally, the following algorithm is adopted to rank the limited intention set corresponding to the entity to be queried: a learning-to-rank model, or a syntactic analysis.
Optionally, before determining the entity to be queried in the natural language query statement from the knowledge base, the method further includes: matching the pinyin of each word in the natural language query sentence with the pinyin of each preset entity name in a preset entity name list to obtain a matching result, wherein the preset entity name list comprises a plurality of preset entity names and the pinyins thereof; and if the matching result shows that the pinyin with the preset entity name is matched with the pinyin of the term in the natural language query sentence, updating the term into the matched preset entity name.
Optionally, before determining the entity to be queried in the natural language query statement from the knowledge base, the method further includes: performing a pre-processing operation on the natural language query statement, the pre-processing operation selected from filtering sensitive words and font conversions.
Optionally, the entity name is selected from the names of fund products, fund managers and fund companies, or from the names of insurance products, insurance managers and insurance companies, or from the names of financing products, financing managers and financing companies.
In order to solve the above technical problem, an embodiment of the present invention further discloses an information query apparatus, where the information query apparatus includes: the natural language query sentence acquisition module is used for acquiring a natural language query sentence input by a user; an entity name identification module, configured to determine an entity to be queried in the natural language query statement from a knowledge base, where the entity to be queried includes a query entity name; an intention identification module for identifying the query intention of the natural language query statement; and the answer determining module is used for determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation.
The embodiment of the invention also discloses a storage medium, wherein a computer instruction is stored on the storage medium, and the steps of the information query method are executed when the computer instruction runs.
The embodiment of the invention also discloses an intelligent terminal which comprises a memory and a processor, wherein the memory is stored with a computer instruction capable of running on the processor, and the processor executes the steps of the information query method when running the computer instruction.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
in the technical scheme of the invention, the name of a query entity in the natural language query sentence and the query intention of the natural language query sentence can be identified and determined for the natural language query sentence input by a user; the corresponding relation between the combination of the entity name and the intention and the answer can be determined through the pre-established preset mapping relation, so that the answer of the natural language query statement can be determined by utilizing the query entity name in the natural language query statement, the query intention of the natural language query statement and the preset mapping relation. According to the technical scheme, the answer is determined by the combination of the entity name and the intention, so that the accuracy and pertinence of answer determination can be guaranteed, the problem that the answer can be determined only by secondary query of a user in the prior art is avoided, and the convenience of information query and the user experience are improved.
Further, when determining the answer of the natural language query statement, it is determined that the entity name in the preset mapping relationship is matched with the query entity name, and the intent in the preset mapping relationship is matched with the query intent, and then it is determined that the answer in the preset mapping relationship is the answer of the natural language query statement, and the accuracy of the matched answer is ensured by a way of matching both the entity name and the intent.
Further, fuzzy matching is carried out on the pinyin of the entity name and the pinyin of each preset entity name in a preset entity name list to obtain a matching result, wherein the preset entity name list comprises a plurality of preset entity names and the pinyins thereof; and if the matching result shows matching, updating the entity name into a matched preset entity name. In the technical scheme of the invention, in order to avoid the query error caused by wrongly written characters in the natural language query sentence input by the user, the entity name can be updated in a pinyin matching mode, so that the accuracy of the finally matched answer is further ensured.
Drawings
FIG. 1 is a flow chart of a method for querying information according to an embodiment of the present invention;
FIG. 2 is a flowchart of one embodiment of step S104 shown in FIG. 1;
FIG. 3 is a partial flow chart of a method for querying information in accordance with an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an information query apparatus according to an embodiment of the present invention.
Detailed Description
As described in the background, the information queried by the query methods in the prior art is generally general and tedious, and the user usually has a clear intention to query, for example, the user may only want to see what stocks are in the fund position, or see how the historical performance of the fund manager is in a fund, and the search engine in the prior art is difficult to query in one step, and needs to perform a second filtering of the information after the first query to obtain effective information.
In the technical scheme of the invention, the name of a query entity in the natural language query sentence and the query intention of the natural language query sentence can be identified and determined for the natural language query sentence input by a user; the corresponding relation between the combination of the entity name and the intention and the answer can be determined through the pre-established preset mapping relation, so that the answer of the natural language query statement can be determined by utilizing the query entity name in the natural language query statement, the query intention of the natural language query statement and the preset mapping relation. According to the technical scheme, the answer is determined by the combination of the entity name and the intention, so that the accuracy and pertinence of answer determination can be guaranteed, the problem that the answer can be determined only by secondary query of a user in the prior art is avoided, and the convenience of information query and the user experience are improved.
The "natural language query statement" referred to in the embodiments of the present invention refers to a statement input by a user for query, and may specifically be text or voice data.
The "query entity name" in the embodiment of the present invention refers to a name of an entity appearing in a natural language query statement, such as a fund name, a fund manager name, a fund company name, and the like.
The term "query intention" in the embodiments of the present invention refers to an intention represented by a natural language query statement, such as query for taken position, query for company profile, and the like.
The "preset mapping relationship" in the embodiment of the present invention refers to a pre-established correspondence between a combination of an entity name and an intention and an answer, and specifically, the preset mapping relationship may include a plurality of combinations of an entity name and an intention and corresponding answers.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a flowchart of an information query method according to an embodiment of the present invention.
The information query method shown in fig. 1 may be executed by any intelligent terminal device capable of interacting with a user, and the intelligent terminal device may specifically be any device capable of interacting with a user, such as a computer, an intelligent robot, and the like.
The information query method may include the steps of:
step S101: acquiring a natural language query sentence input by a user;
step S102: determining an entity to be queried in the natural language query statement from a knowledge base, wherein the entity to be queried comprises a query entity name;
step S103: identifying a query intent of the natural language query statement;
step S104: and determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation.
It should be noted that the sequence numbers of the steps in this embodiment do not represent a limitation on the execution sequence of the steps. For example, step S102 and step S103 may be executed simultaneously, or step S102 may be executed earlier than step S103, or step S103 may be executed earlier than step S102, which is not limited in this embodiment of the present invention.
In this embodiment, the natural language query sentence input by the user may be a natural language. More specifically, the natural language query statement may be in text, speech, or the like. For example, in a specific application scenario, a user inputs voice data, the voice data may be converted into a text, and the subsequent entity name recognition and intention recognition processes are performed based on the text.
In a specific implementation of step S102, the entity list of the knowledge base may be sorted for the natural language query statement input by the user, and the query entity name in the natural language query statement is determined according to the sorted top 1 result. For the specific sorting algorithm, a learning-to-rank algorithm based on deep learning may be adopted, and any other implementable entity name recognition algorithm, such as a syntactic analysis algorithm, may also be used, which is not limited in this embodiment of the present invention.
For specific implementation of the learning-to-rank algorithm (or learning-to-rank model) and the syntax analysis algorithm, reference may be made to the prior art, and the embodiments of the present invention are not described herein again.
Taking a fund product as an example, the entity name may include the following three categories: fund products, fund managers, and fund companies. The user inputs the natural language query sentence "the rainbow fund company is not good, and the entity name" the rainbow fund company "can be obtained through step S102.
In a specific implementation of step S103, a query intent to obtain a natural language query statement may be identified. Specifically, the intentions corresponding to the entity can be ranked according to the determined entity name through a pre-trained model, and the ranked top 1 result is used as an intention result. For a specific sorting algorithm, a learning-to-rank algorithm based on deep learning may be adopted, and any other implementable algorithm, such as a syntax analysis algorithm, may also be used, which is not limited by the embodiment of the present invention.
Specifically, the trained neural network is used for training a learning-to-rank model to perform intention recognition on the natural language query statement.
For example, the user inputs a natural language query sentence "rainbow fund company is not good" and the query intention is "company profile" through step S103.
Up to this point, by determining the query entity name and the query intention of the natural language query sentence in steps S102 and S103, the combination of the above two parameters can clearly indicate the content desired by the user.
In this embodiment, before the natural language query sentence of the user is obtained, a preset mapping relationship may be established in advance to establish a correspondence between a combination of an entity name and an intention and an answer.
Further, in step S104, an answer to the natural language query statement may be determined by using the name of the query entity in the natural language query statement, the query intent of the natural language query statement, and a preset mapping relationship. The preset mapping relation comprises a plurality of entity name and intention combinations and corresponding answers.
In a specific implementation, the preset mapping relationship may also be a mapping relationship between a combination of an entity name and an intent and a query instruction, and each query instruction may determine a unique answer through a query operation. For example, the Query instruction may be a Structured Query Language (SQL) statement, by which an answer may be queried in a database and fed back to the user.
Specifically, the preset mapping relationship may be stored in a database, and the preset mapping relationship may be called from the database when necessary.
According to the embodiment of the invention, the answer is determined by using the combination of the entity name and the intention, so that the accuracy and pertinence of the answer determination can be ensured, the problem that the answer can be determined only by the secondary query of the user in the prior art is avoided, and the convenience of information query and the user experience are improved.
In one non-limiting embodiment of the invention, the entity name is selected from the names of a fund product, a fund manager, and a fund company, or from the names of an insurance product, an insurance manager, and an insurance company, or from the names of a financing product, a financing manager, and a financing company.
In other words, the information query method of the embodiment of the invention can query the fund related information, the insurance related information and the financing related information so as to meet different requirements of users in different application scenes.
In an embodiment of the present invention, the information query method shown in fig. 1 may further include the following steps: and feeding back the answer to the user.
Specifically, the answer may be presented to the user in a preset format, for example, in a text manner; or the answer can be broadcasted in a voice mode, and the answer can be displayed in a mode of combining the text and the answer.
In an embodiment of the present invention, referring to fig. 2, step S104 shown in fig. 1 may include the following steps:
step S201: matching the query entity name with entity names in a plurality of preset mapping relations;
step S202: if the entity name in the preset mapping relation is matched with the query entity name, matching the intention in the matched preset mapping relation with the query intention;
step S203: and if the intention in the matched preset mapping relation is matched with the query intention, taking the answer in the matched preset mapping relation as the answer corresponding to the natural language query statement.
It should be noted that, regarding step S201 and step S202, the following steps may be substituted: firstly, matching the query intention with intentions in a plurality of preset mapping relations; if the intention in the preset mapping relationship is matched with the query intention, matching the entity name in the preset mapping relationship with the query entity name, which is not limited in the embodiment of the present invention.
In this embodiment, when determining an answer to a natural language query statement, it is determined that an entity name in a preset mapping relationship matches a query entity name, and an intention in the preset mapping relationship matches a query intention, and then it is determined that the answer in the preset mapping relationship is an answer to the natural language query statement, and accuracy of the matched answer is ensured by a way of matching both the entity name and the intention.
Further, if only an intention matching the query intention exists in the same preset mapping relationship, or the entity name matching the query entity name, the answer corresponding to the natural language query statement cannot be determined. In this case, a preset guide statement may be returned to the user to instruct the user to update the natural language query statement. For example, "do you can specify your question again", "you can ask me some knowledge about my fund", etc.
More specifically, step S203 shown in fig. 2 may include the steps of: directly taking an answer corresponding to the combination of the entity name and the intention in the matched preset mapping relation as an answer corresponding to the natural language query statement; or determining a query instruction corresponding to the combination of the entity name and the intention in the matched preset mapping relation, and taking an answer obtained by executing the query instruction as an answer corresponding to the natural language query statement.
That is, the combination of the entity name and the intent in the preset mapping relationship may directly correspond to the answer, and the preset mapping relationship includes the combination of the entity name and the intent and the answer, in which case, the answer in the matched preset mapping relationship may be directly used as the answer corresponding to the natural language query.
The combination of the entity name and the intent in the preset mapping relationship may indirectly correspond to the answer, that is, the preset mapping relationship includes the combination of the entity name and the intent and a query instruction, and the answer may be obtained by executing the query instruction, in which case, the answer obtained by executing the query instruction may be used as the answer corresponding to the natural language query statement.
It should be noted that the query instruction may be an SQL statement, or may be any other implementable unstructured query instruction capable of executing a query operation, which is not limited in this embodiment of the present invention.
In a preferred embodiment of the present invention, step S102 shown in fig. 1 may include the following steps: and inputting the natural language query sentence into a pre-trained entity name recognition model to obtain an entity name in the natural language query sentence, wherein when the entity name recognition model is trained by using training data, the training data comprises the full name and the short name of each entity name.
In practical applications, the names of entities that a user needs to query are relatively long, and the user usually queries the entities by using the names of the entities for short, taking fund products as an example, the names of the funds are usually very long, such as "hua le xiang healthy mix", "hua shi yun biao mix", "bokeyue yue yi short term financing bond", and the like, but the user generally cannot remember the full names of the funds, and input natural language query statements are usually the names of the saved funds, such as "hua xiayue", "hua yue yi mix", "bos yue", which results in no query result.
When the entity name recognition model is used for recognizing the entity name of the natural language query sentence, in order to ensure the comprehensiveness and the accuracy of the entity name recognition, the comprehension names and the abbreviation of all entity names can be used for constructing training data, and the entity name recognition model is trained by using the training data, so that the trained entity name recognition model can recognize the comprehension names or the abbreviation of all entity names, the entity names are prevented from being omitted, and the accuracy of information query is ensured.
In a non-limiting embodiment of the present invention, referring to fig. 3, step S102 shown in fig. 1 may further include the following steps before:
step S301: matching the pinyin of each word in the natural language query sentence with the pinyin of each preset entity name in a preset entity name list to obtain a matching result, wherein the preset entity name list comprises a plurality of preset entity names and the pinyins thereof;
step S302: and if the matching result shows that the pinyin with the preset entity name is matched with the pinyin of the term in the natural language query sentence, updating the term into the matched preset entity name.
In the specific implementation, because the natural language query statement is input by the user through the input method, the wrongly written characters are inevitably generated, or the user intentionally inputs the wrong characters, the wrongly written characters in the natural language query statement need to be corrected, especially the wrongly written characters are corrected according to the entity name in the natural language query statement, so as to ensure the correctness of the entity name identification in the subsequent steps.
Specifically, a preset entity name list may be pre-established, where the preset entity name list includes a plurality of preset entity names and pinyins thereof. And pinyin conversion can be carried out on the natural language query sentence to obtain the pinyin of each term in the natural language query sentence.
In the specific implementation of step S301 and step S302, the pinyin of each term in the natural language query sentence may be matched with the pinyin of each preset entity name in the preset entity name list, for example, fuzzy matching may be performed. And if the pinyin of the preset entity name matched with the pinyin of the word exists, updating the word into the matched preset entity name.
In the embodiment of the invention, in order to avoid the query error caused by wrongly written characters in the natural language query sentence input by the user, the entity name can be updated in a pinyin matching mode, so that the accuracy of the finally matched answer is further ensured.
In a specific application scenario, a user inputs a natural language query statement "Tianhong fund company is good and bad", wherein the pinyin of "Tianhong fund" is the same as the pinyin of "Tianhong fund" in a preset entity name list, so that the "Tianhong fund" is updated to the "Tianhong fund"; the entity name identification step identifies and obtains the name of the inquired entity as 'Tianhong fund', and the natural language inquiry statement is intended as 'company general'.
In a non-limiting embodiment of the present invention, step S102 shown in fig. 1 may further include the following steps: performing a pre-processing operation on the natural language query statement, the pre-processing operation selected from filtering sensitive words and font conversions.
In particular implementations, sensitive words in the natural-language query statement may be filtered prior to performing entity name recognition and intent recognition, e.g., the sensitive words may include abusive words, sensitive names, sensitive nouns, and so forth. When the sensitive word is matched in the natural language query sentence, the sensitive word can be directly filtered, and the subsequent steps are carried out. Or the preset statement can be directly returned without subsequent processing flow.
In a specific implementation, before performing the entity name recognition and the intent recognition, font conversion may be performed on the fonts of the natural language query statement, so that the fonts of the terms in the natural language query statement are consistent. Specifically, when the natural language query sentence is Chinese, the natural language query sentence is uniformly converted into simplified Chinese.
The specific sensitive word setting or the specific conversion font setting may be adaptively configured and modified according to an actual application environment, which is not limited in this embodiment of the present invention.
In a specific application scenario, a user inputs a natural language query sentence "huaxia corporation spam", identifies a sensitive word "spam", in which case a specific dialect can be directly returned, or the sensitive word can be filtered to obtain "huaxia corporation", and continues to execute subsequent steps.
Referring to fig. 4, an embodiment of the present invention further discloses an information query apparatus 40, where the information query apparatus 40 may include a natural language query sentence acquisition module 401, an entity name identification module 402, an intention identification module 403, and an answer determination module 404.
The natural language query statement acquisition module 401 is configured to acquire a natural language query statement input by a user; the entity name identification module 402 is configured to sort the entities in the entity list through the natural language query statement; the intention identifying module 403 is configured to sort the intentions corresponding to the entity according to the entity name determined by the entity name identifying module 402, so as to obtain the query intention of the natural language query statement; the answer determining module 404 is configured to determine an answer corresponding to the natural language query statement according to a combination of the query entity name and the query intention and a preset mapping relationship, where the preset mapping relationship includes a combination of a plurality of entity names and intents and an answer corresponding to the entity names and intents.
In the embodiment of the invention, for the natural language query statement input by a user, the name of a query entity in the natural language query statement and the query intention of the natural language query statement can be identified and determined; the corresponding relation between the combination of the entity name and the intention and the answer can be determined through the pre-established preset mapping relation, so that the answer of the natural language query statement can be determined by utilizing the query entity name in the natural language query statement, the query intention of the natural language query statement and the preset mapping relation. According to the embodiment of the invention, the answer is determined by using the combination of the entity name and the intention, so that the accuracy and pertinence of the answer determination can be ensured, the problem that the answer can be determined only by the secondary query of the user in the prior art is avoided, and the convenience of information query and the user experience are improved.
For more details of the operation principle and the operation mode of the information query device 40, reference may be made to the relevant descriptions in fig. 1 to fig. 3, which are not described herein again.
The embodiment of the invention also discloses a storage medium, wherein computer instructions are stored on the storage medium, and when the computer instructions are operated, the steps of the method shown in the figure 1, the figure 2 or the figure 3 can be executed. The storage medium may include ROM, RAM, magnetic or optical disks, etc. The storage medium may further include a non-volatile memory (non-volatile) or a non-transitory memory (non-transient), and the like.
The embodiment of the invention also discloses an intelligent terminal which can comprise a memory and a processor, wherein the memory stores computer instructions capable of running on the processor. The processor, when executing the computer instructions, may perform the steps of the methods shown in fig. 1, fig. 2, or fig. 3. The intelligent terminal comprises but is not limited to terminal equipment such as a mobile phone, a computer, a tablet computer and the like.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (13)
1. An information query method, comprising:
acquiring a natural language query sentence input by a user;
determining an entity to be queried in the natural language query statement from a knowledge base, wherein the entity to be queried comprises a query entity name;
identifying a query intent of the natural language query statement;
and determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation.
2. The information query method of claim 1, wherein the determining the answer corresponding to the natural language query statement according to the combination of the query entity name and the query intent and a preset mapping relationship comprises:
matching the query entity name with entity names in a plurality of preset mapping relations;
if the entity name in the preset mapping relation is matched with the query entity name, matching the intention in the matched preset mapping relation with the query intention;
and if the intention in the matched preset mapping relation is matched with the query intention, taking the answer in the matched preset mapping relation as the answer corresponding to the natural language query statement.
3. The information query method according to claim 2, wherein the step of using the answer in the matched preset mapping relation as the answer corresponding to the natural language query statement comprises:
directly taking an answer corresponding to the combination of the entity name and the intention in the matched preset mapping relation as an answer corresponding to the natural language query statement;
or determining a query instruction corresponding to the combination of the entity name and the intention in the matched preset mapping relation, and taking an answer obtained by executing the query instruction as an answer corresponding to the natural language query statement.
4. The information query method of claim 1, wherein the determining the entity to be queried in the natural language query statement from the knowledge base comprises:
and sequencing the entity list in the knowledge base according to the natural language query statement input by the user, and taking the entity with the top sequence as the entity to be queried.
5. The information query method of claim 1, wherein the following algorithm is used to rank the entity lists in the knowledge base: a learning-to-rank model, or syntactic analysis.
6. The information query method of claim 1, wherein the identifying the query intent of the natural language query statement comprises:
and sequencing the limited intention set corresponding to the entity to be queried according to the entity to be queried and the natural language query statement.
7. The information query method according to claim 6, wherein the limited intention set corresponding to the entity to be queried is ranked by using the following algorithm: a learning-to-rank model, or a syntactic analysis.
8. The information query method of claim 1, wherein the determining the entity to be queried in the natural language query statement from the knowledge base further comprises:
matching the pinyin of each word in the natural language query sentence with the pinyin of each preset entity name in a preset entity name list to obtain a matching result, wherein the preset entity name list comprises a plurality of preset entity names and the pinyins thereof;
and if the matching result shows that the pinyin with the preset entity name is matched with the pinyin of the term in the natural language query sentence, updating the term into the matched preset entity name.
9. The information query method of claim 1, wherein the determining the entity to be queried in the natural language query statement from the knowledge base further comprises:
performing a pre-processing operation on the natural language query statement, the pre-processing operation selected from filtering sensitive words and font conversions.
10. The information query method of claim 1, wherein the entity name is selected from the names of fund products, fund managers and fund companies, or from the names of insurance products, insurance managers and insurance companies, or from the names of financial products, financial managers and financial companies.
11. An information inquiry apparatus, comprising:
the natural language query sentence acquisition module is used for acquiring a natural language query sentence input by a user;
an entity name identification module, configured to determine an entity to be queried in the natural language query statement from a knowledge base, where the entity to be queried includes a query entity name;
an intention identification module for identifying the query intention of the natural language query statement;
and the answer determining module is used for determining an answer corresponding to the natural language query statement according to the combination of the query entity name and the query intention and a preset mapping relation.
12. A storage medium having stored thereon computer instructions, wherein the computer instructions are operable to perform the steps of the information query method of any one of claims 1 to 10.
13. An intelligent terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor executes the computer instructions to perform the steps of the information query method according to any one of claims 1 to 10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869534.0A CN110765342A (en) | 2019-09-12 | 2019-09-12 | Information query method and device, storage medium and intelligent terminal |
| PCT/CN2020/083561 WO2021047169A1 (en) | 2019-09-12 | 2020-04-07 | Information query method and apparatus, storage medium, and smart terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910869534.0A CN110765342A (en) | 2019-09-12 | 2019-09-12 | Information query method and device, storage medium and intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110765342A true CN110765342A (en) | 2020-02-07 |
Family
ID=69329796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910869534.0A Pending CN110765342A (en) | 2019-09-12 | 2019-09-12 | Information query method and device, storage medium and intelligent terminal |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110765342A (en) |
| WO (1) | WO2021047169A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538894A (en) * | 2020-06-19 | 2020-08-14 | 腾讯科技（深圳）有限公司 | Query feedback method and device, computer equipment and storage medium |
| CN112131016A (en) * | 2020-09-15 | 2020-12-25 | 北京值得买科技股份有限公司 | Application program internal data processing method, device and equipment |
| CN112287088A (en) * | 2020-11-20 | 2021-01-29 | 四川长虹电器股份有限公司 | Intelligent man-machine interaction query method, system, computer equipment and storage medium |
| CN112463932A (en) * | 2020-12-14 | 2021-03-09 | 北京明略软件系统有限公司 | Method, device and equipment for information query |
| WO2021047169A1 (en) * | 2019-09-12 | 2021-03-18 | 竹间智能科技（上海）有限公司 | Information query method and apparatus, storage medium, and smart terminal |
| CN116628004A (en) * | 2023-05-19 | 2023-08-22 | 北京百度网讯科技有限公司 | Information query method, device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330120A (en) * | 2017-07-14 | 2017-11-07 | 三角兽（北京）科技有限公司 | Inquire answer method, inquiry answering device and computer-readable recording medium |
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN108170859A (en) * | 2018-01-22 | 2018-06-15 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of speech polling |
| CN109522393A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
| CN109800407A (en) * | 2017-11-15 | 2019-05-24 | 腾讯科技（深圳）有限公司 | Intension recognizing method, device, computer equipment and storage medium |
| CN110222045A (en) * | 2019-04-23 | 2019-09-10 | 平安科技（深圳）有限公司 | A kind of data sheet acquisition methods, device and computer equipment, storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866498A (en) * | 2014-02-24 | 2015-08-26 | 华为技术有限公司 | Information processing method and device |
| CN106570180B (en) * | 2016-11-10 | 2020-05-22 | 北京百度网讯科技有限公司 | Voice search method and device based on artificial intelligence |
| CN109739964A (en) * | 2018-12-27 | 2019-05-10 | 北京拓尔思信息技术股份有限公司 | Knowledge data providing method, device, electronic equipment and storage medium |
| CN110765342A (en) * | 2019-09-12 | 2020-02-07 | 竹间智能科技（上海）有限公司 | Information query method and device, storage medium and intelligent terminal |
-
2019
- 2019-09-12 CN CN201910869534.0A patent/CN110765342A/en active Pending
-
2020
- 2020-04-07 WO PCT/CN2020/083561 patent/WO2021047169A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918634A (en) * | 2017-06-27 | 2018-04-17 | 上海壹账通金融科技有限公司 | Intelligent answer method, apparatus and computer-readable recording medium |
| CN107330120A (en) * | 2017-07-14 | 2017-11-07 | 三角兽（北京）科技有限公司 | Inquire answer method, inquiry answering device and computer-readable recording medium |
| CN109800407A (en) * | 2017-11-15 | 2019-05-24 | 腾讯科技（深圳）有限公司 | Intension recognizing method, device, computer equipment and storage medium |
| CN108170859A (en) * | 2018-01-22 | 2018-06-15 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of speech polling |
| CN109522393A (en) * | 2018-10-11 | 2019-03-26 | 平安科技（深圳）有限公司 | Intelligent answer method, apparatus, computer equipment and storage medium |
| CN110222045A (en) * | 2019-04-23 | 2019-09-10 | 平安科技（深圳）有限公司 | A kind of data sheet acquisition methods, device and computer equipment, storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021047169A1 (en) * | 2019-09-12 | 2021-03-18 | 竹间智能科技（上海）有限公司 | Information query method and apparatus, storage medium, and smart terminal |
| CN111538894A (en) * | 2020-06-19 | 2020-08-14 | 腾讯科技（深圳）有限公司 | Query feedback method and device, computer equipment and storage medium |
| CN112131016A (en) * | 2020-09-15 | 2020-12-25 | 北京值得买科技股份有限公司 | Application program internal data processing method, device and equipment |
| CN112287088A (en) * | 2020-11-20 | 2021-01-29 | 四川长虹电器股份有限公司 | Intelligent man-machine interaction query method, system, computer equipment and storage medium |
| CN112463932A (en) * | 2020-12-14 | 2021-03-09 | 北京明略软件系统有限公司 | Method, device and equipment for information query |
| CN116628004A (en) * | 2023-05-19 | 2023-08-22 | 北京百度网讯科技有限公司 | Information query method, device, electronic equipment and storage medium |
| CN116628004B (en) * | 2023-05-19 | 2023-12-08 | 北京百度网讯科技有限公司 | Information query method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021047169A1 (en) | 2021-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765342A (en) | Information query method and device, storage medium and intelligent terminal | |
| US10262062B2 (en) | Natural language system question classifier, semantic representations, and logical form templates | |
| CN106202059B (en) | Machine translation method and machine translation device | |
| US9582757B1 (en) | Scalable curation system | |
| US9524291B2 (en) | Visual display of semantic information | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| CN114757176B (en) | Method for acquiring target intention recognition model and intention recognition method | |
| CN112948534A (en) | Interaction method and system for intelligent man-machine conversation and electronic equipment | |
| US11526512B1 (en) | Rewriting queries | |
| CN110502227A (en) | The method and device of code completion, storage medium, electronic equipment | |
| CN116521841B (en) | Method, device, equipment and medium for generating reply information | |
| CN116737908A (en) | Knowledge question-answering method, device, equipment and storage medium | |
| US20230252222A1 (en) | Formatting module, system and method for formatting an electronic character sequence | |
| CN111400458A (en) | Automatic generalization method and device | |
| CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
| CN110674276A (en) | Robot self-learning method, robot terminal, device and readable storage medium | |
| CN117251455A (en) | Intelligent report generation method and system based on large model | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN111639160A (en) | Domain identification method, interaction method, electronic device and storage medium | |
| CN114490986B (en) | Computer-implemented data mining method, device, electronic equipment and storage medium | |
| CN108959327B (en) | Service processing method, device and computer readable storage medium | |
| CN112989003B (en) | Intention recognition method, device, processing equipment and medium | |
| CN112860873B (en) | Intelligent response method, device and storage medium | |
| CN114896382A (en) | Artificial intelligent question-answering model generation method, question-answering method, device and storage medium | |
| CN114546326A (en) | Virtual human sign language generation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |