CN112559710A - Material information query method and query device - Google Patents
Material information query method and query device Download PDFInfo
- Publication number
- CN112559710A CN112559710A CN202011529667.2A CN202011529667A CN112559710A CN 112559710 A CN112559710 A CN 112559710A CN 202011529667 A CN202011529667 A CN 202011529667A CN 112559710 A CN112559710 A CN 112559710A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- professional
- searching
- word segmentation
- 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
- G06F16/30—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
-
- 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
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The embodiment of the invention discloses a material information query method and a query device, relates to the technical field of artificial intelligence, and can improve the query efficiency of material information. The method comprises the following steps: acquiring target voice information carrying a material name and a material specification model; converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field; performing word segmentation on the text information by using a word segmentation technology to obtain a target key word group, wherein the target key word group comprises professional terms of the material name and the material specification model; and searching target material information matched with the professional terms in the target key phrase in a material information base. The invention is suitable for inquiring material information.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a material information query method and a query device.
Background
Material is a special term in the production field of China. It is customary for the manufacturing industry to refer collectively to everything outside the end product, which is circulated in the manufacturing field (whether it comes from manufacturing or life information), fuel, parts, semi-finished goods, outside service, and scrap, waste, and various wastes that must be generated during the manufacturing process as "materials".
At present, in the process of material purchase, cost accounting or product production, the information of the material is often required to be inquired; however, in the current query of the material information, complicated characters such as material names, material numbers and the like are generally required to be input, which causes the problem of low query efficiency of the material information.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for querying material information, which can improve the query efficiency of material information.
In a first aspect, an embodiment of the present invention provides a method for querying material information, where the method includes: acquiring target voice information carrying a material name and a material specification model; converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field; performing word segmentation on the text information by using a word segmentation technology to obtain a target key word group, wherein the target key word group comprises professional terms of the material name and the material specification model; and searching target material information matched with the professional terms in the target key phrase in a material information base.
Optionally, after finding the target material information matched with the professional term in the target keyword group, the method further includes: and carrying out voice broadcast on the target material information.
Optionally, the target material information includes a material price; searching target material information matched with the professional terms in the target key phrase in a material information base, wherein the searching comprises the following steps: searching a target material number matched with the professional term in a material number library, wherein the material number library stores the mapping relation between the material number and the professional term of the material name and the material specification model; and searching for the material price corresponding to the target material number in the material information base, wherein the mapping relation between the material number and the material price is stored in the material information base.
Optionally, the material number matched with the professional term is searched in the material number library; the method comprises the following steps: searching for alternative material numbers matched with at least one item in the professional terms in the material number library; calculating the number of matching items of each alternative material number and the professional term; and taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
Optionally, the word segmentation technology is used for carrying out word segmentation on the text information to obtain a target key word group; the method comprises the following steps: customizing a word segmentation device dictionary according to the professional terms of the material name and the specification model; and utilizing the word segmentation device to segment words of the character information to obtain a target key word group.
In a second aspect, an embodiment of the present invention provides a material information query apparatus, where the apparatus includes: the acquisition unit is used for acquiring target voice information carrying the material name and the material specification model; the conversion unit is used for converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field; the word segmentation unit is used for segmenting the word information by utilizing a word segmentation technology to obtain a target key word group, wherein the target key word group comprises the material name and the professional term of the material specification model; and the searching unit is used for searching the target material information matched with the professional terms in the target key phrase in the material information base.
Optionally, the apparatus further comprises: and the voice broadcasting unit is used for carrying out voice broadcasting on the target material information.
Optionally, the target material information includes a material price; the search unit is specifically configured to: searching a target material number matched with the professional term in a material number library, wherein the material number library stores the mapping relation between the material number and the professional term of the material name and the material specification model; and searching for the material price corresponding to the target material number in the material information base, wherein the mapping relation between the material number and the material price is stored in the material information base.
Optionally, the material number matched with the professional term is searched in the material number library; the method comprises the following steps: searching for alternative material numbers matched with at least one item in the professional terms in the material number library; calculating the number of matching items of each alternative material number and the professional term; and taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
Optionally, the word segmentation unit is specifically configured to: customizing a word segmentation device dictionary according to the professional terms of the material name and the specification model; and utilizing the word segmentation device to segment words of the character information to obtain a target key word group.
According to the material information query method and the query device provided by the embodiment of the invention, target voice information carrying the material name and the material specification model is obtained; converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field; performing word segmentation on the text information by using a word segmentation technology to obtain a target key word group, wherein the target key word group comprises professional terms of the material name and the material specification model; and searching target material information matched with the professional terms in the target key phrase in a material information base. Therefore, based on the voice processing and full-text retrieval technology, a user can query the target material information only by giving the voice information without complicated character input, and the query efficiency of the material information is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a material information query method according to an embodiment of the present invention;
fig. 2 is a schematic partial flowchart of a material information query method according to a first embodiment of the present invention;
fig. 3 is another schematic flow chart of a part of a material information query method according to a first embodiment of the present invention;
fig. 4 is a schematic flow chart of another part of a material information query method according to a first embodiment of the present invention;
fig. 5 is a schematic flowchart of a specific material information query method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a material information query device according to a second embodiment of the present invention;
FIG. 7 is a diagram illustrating a working process of a speech translation module according to a second embodiment of the present invention;
FIG. 8 is a diagram illustrating the operation of the full-text search module according to a second embodiment of the present invention;
fig. 9 is a schematic structural diagram of another material information query device according to a second embodiment of the present invention;
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
As shown in fig. 1, an embodiment of the present invention provides a method for querying material information, where the method includes:
s101, acquiring target voice information carrying a material name and a material specification model;
in the step, each material corresponds to a material name and a material specification model, for example, for a forklift, the name of the forklift is 3t, the specification of the forklift is 5t, and the like, but the forklift of 3t may be different models of different manufacturers such as a resultant forklift, a Jianghuai forklift and the like.
The target voice information may be collected from a user, for example: the voice input of the user is collected by the microphone device. In the target voice information, besides the material name and the material specification model, other contents may be included, for example, the target voice information may be "how much money the Jianghuai forklift of 3t is queried".
S102, converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field;
converting the target voice information into character information, namely converting voice stream data into character stream data; specifically, the speech data stream may be modeled based on a deep full-sequence convolutional neural network speech recognition framework, and the speech data stream may be translated into words according to a correspondence between modeled phonemes and words.
Since there may be some popular names, specification models, etc. of some materials, such as printers, etc., when the correspondence between phonemes and words is established in the above steps, one word may correspond to multiple phonemes, and preferably, the word may be a term in the field of the material. At this time, for the printer, whether the target voice message is "printer" or "printer", it is translated into the term "printer".
S103, segmenting the word information by utilizing a segmentation technology to obtain a target key phrase, wherein the target key phrase comprises the material name and the professional term of the material specification model;
in this step, the target keyword group includes at least one target keyword, and each target keyword group is combined into the text information; as shown in fig. 2, optionally, the word segmentation is performed on the text information by using a word segmentation technique to obtain a target keyword group; the method can comprise the following steps:
s1031, self-defining a word segmentation device dictionary according to the professional terms of the material name and the specification model;
s1032, the word segmentation is carried out on the character information by the word segmentation device, and a target key word group is obtained.
In the embodiment, Chinese word segmentation can be performed through the word segmentation device 'ik _ smart', and before Chinese word segmentation is performed through the word segmentation device 'ik _ smart', a word segmentation device dictionary is customized according to professional terms of material names and specification models, so that the word segmentation accuracy of the word segmentation device can be improved.
S104, searching target material information matched with the professional terms in the target key phrase in a material information base.
In the step, the material information base stores the mapping relationship between the material information and the professional terms of the material name and the material specification model, that is, in the material information base, each piece of material information corresponds to the professional term of the corresponding material name and specification model.
The searching for the target material information matched with the professional term in the target key phrase in the material information base may include: searching target material information with the highest matching degree with the professional terms through full-text index; specifically, data can be retrieved through an elastic search full-text index, the material information with the highest word segmentation matching degree score is inquired, and the material information base is inquired according to the professional term and the material information is obtained.
In the material information query method provided by this embodiment, target voice information carrying a material name and a material specification model is obtained; converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field; performing word segmentation on the text information by using a word segmentation technology to obtain a target key word group, wherein the target key word group comprises professional terms of the material name and the material specification model; and searching target material information matched with the professional terms in the target key phrase in a material information base. Therefore, based on the voice processing and full-text retrieval technology, a user can query the target material information only by giving the voice information without complicated character input, and the query efficiency of the material information is greatly improved.
Optionally, after finding the target material information matched with the professional term in the target keyword group, the method further includes: and carrying out voice broadcast on the target material information.
This embodiment, target material information can include the material price, at this moment, it is right target material information carries out voice broadcast, can include: and converting the obtained material price data into voice stream data, and calling an earphone device through a browser to broadcast the voice stream data.
Will through voice broadcast's form target material information transfer gives the user, under some occasions, can liberate user's both hands and both eyes to promote user's work efficiency.
As shown in fig. 3, optionally, the target material information includes a material price; searching target material information matched with the professional terms in the target key phrase in a material information base, wherein the searching comprises the following steps:
s1041, searching a target material number matched with the professional term in a material number library, wherein the mapping relation between the material number and the professional term of the material name and the material specification model is stored in the material number library;
s1042, searching a material price corresponding to the target material number in the material information base, wherein a mapping relation between the material number and the material price is stored in the material information base.
In this embodiment, because in the storage system at the background, every kind of material all corresponds a serial number, convenient management, consequently, above-mentioned inquiry mode can adapt to the save mode of material information in the system, the convenient inquiry to the material price.
As shown in fig. 4, optionally, in the above embodiment, the material number matching the term in the material number library is searched; the method comprises the following steps:
s10411, searching for alternative material numbers matched with at least one item in the professional terms in the material number library;
s10412, calculating the number of matching items of each alternative material number and the professional term;
and S10413, taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
In this embodiment, the more the number of the candidate material numbers matching the professional term is, the higher the matching degree of the candidate material numbers with the professional term is, and the target material number is equivalent to the material number with the highest matching degree with the material name and the material specification model in the target voice information. The more accurate the price of the material corresponding to the target material number found in the step S1042 is.
In order to better understand the present invention, the following description is provided for a material information query method provided by the present invention through a specific embodiment:
as shown in fig. 5, the method for querying material information provided in this embodiment includes:
s201, according to the operation of opening a system help function by a user, starting a browser microphone for monitoring, and monitoring the voice input of the user in real time;
s202, acquiring voice stream data such as material names, specification models and the like spoken by a user through a microphone;
s203, submitting the voice stream data to a voice translation module;
s204, the voice translation module translates the voice stream data into character stream data;
s205, judging whether the voice input operation of the user is stopped for 3S;
s206, if yes, submitting the character stream data to a full text retrieval module;
s207, the full-text retrieval module carries out word segmentation on the character stream data, and full-text index retrieval is carried out to inquire the price of the material;
s208, the voice broadcasting module receives the material price data and synthesizes voice;
and S209, broadcasting the synthesized voice data through an earphone device.
Example two
As shown in fig. 6, an embodiment of the present invention provides a material information query apparatus, where the apparatus includes: the acquiring unit 21 is configured to acquire target voice information carrying a material name and a material specification model; the conversion unit 22 is configured to convert the target voice information into text information, where the material name and the material specification model in the target voice information are converted into a professional term in the material field; a word segmentation unit 23, configured to perform word segmentation on the text information by using a word segmentation technology to obtain a target key word group, where the target key word group includes the material name and a professional term of the material specification model; and the searching unit 24 is configured to search, in the material information base, target material information matched with the professional term in the target key word group.
In this embodiment, the acquiring unit may specifically be a microphone, the converting unit may also be referred to as a speech translating module, and a working process of the speech translating module is shown in fig. 7.
The word segmentation unit and the search unit can be an integrated full-text search module; the structure of the full-text retrieval module is shown in fig. 8.
As shown in fig. 9, optionally, the apparatus further includes: and the voice broadcasting unit 25 is used for carrying out voice broadcasting on the target material information.
Optionally, the target material information includes a material price; the search unit is specifically configured to: searching a target material number matched with the professional term in a material number library, wherein the material number library stores the mapping relation between the material number and the professional term of the material name and the material specification model; and searching for the material price corresponding to the target material number in the material information base, wherein the mapping relation between the material number and the material price is stored in the material information base.
Optionally, the material number matched with the professional term is searched in the material number library; the method comprises the following steps: searching for alternative material numbers matched with at least one item in the professional terms in the material number library; calculating the number of matching items of each alternative material number and the professional term; and taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
Optionally, the word segmentation unit is specifically configured to: customizing a word segmentation device dictionary according to the professional terms of the material name and the specification model; and utilizing the word segmentation device to segment words of the character information to obtain a target key word group.
The apparatus of this embodiment may be used to implement the technical solution of any one of the method embodiments shown in fig. 1 to 5, and the implementation principle and the technical effect are similar, which are not described herein again.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments.
In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A material information query method is characterized by comprising the following steps:
acquiring target voice information carrying a material name and a material specification model;
converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field;
performing word segmentation on the text information by using a word segmentation technology to obtain a target key word group, wherein the target key word group comprises professional terms of the material name and the material specification model;
and searching target material information matched with the professional terms in the target key phrase in a material information base.
2. The method according to claim 1, wherein after finding the target material information matching the specialized term in the target keyword group, the method further comprises:
and carrying out voice broadcast on the target material information.
3. The method of claim 1 or 2, wherein the target material information comprises a material price; searching target material information matched with the professional terms in the target key phrase in a material information base, wherein the searching comprises the following steps:
searching a target material number matched with the professional term in a material number library, wherein the material number library stores the mapping relation between the material number and the professional term of the material name and the material specification model;
and searching for the material price corresponding to the target material number in the material information base, wherein the mapping relation between the material number and the material price is stored in the material information base.
4. The method according to claim 3, wherein the material number matching the specialized term is searched in a material number library; the method comprises the following steps:
searching for alternative material numbers matched with at least one item in the professional terms in the material number library;
calculating the number of matching items of each alternative material number and the professional term;
and taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
5. The method according to claim 1, wherein the word segmentation is performed on the text information by using a word segmentation technique to obtain a target keyword group; the method comprises the following steps:
customizing a word segmentation device dictionary according to the professional terms of the material name and the specification model;
and utilizing the word segmentation device to segment words of the character information to obtain a target key word group.
6. A material information inquiry device is characterized by comprising:
the acquisition unit is used for acquiring target voice information carrying the material name and the material specification model;
the conversion unit is used for converting the target voice information into character information, wherein the material name and the material specification model in the target voice information are converted into professional terms in the material field;
the word segmentation unit is used for segmenting the word information by utilizing a word segmentation technology to obtain a target key word group, wherein the target key word group comprises the material name and the professional term of the material specification model;
and the searching unit is used for searching the target material information matched with the professional terms in the target key phrase in the material information base.
7. The apparatus of claim 6, further comprising:
and the voice broadcasting unit is used for carrying out voice broadcasting on the target material information.
8. The apparatus of claim 6 or 7, wherein the target material information comprises a material price; the search unit is specifically configured to:
searching a target material number matched with the professional term in a material number library, wherein the material number library stores the mapping relation between the material number and the professional term of the material name and the material specification model;
and searching for the material price corresponding to the target material number in the material information base, wherein the mapping relation between the material number and the material price is stored in the material information base.
9. The apparatus according to claim 8, wherein the material number matching the terminology is searched in a material number library; the method comprises the following steps:
searching for alternative material numbers matched with at least one item in the professional terms in the material number library;
calculating the number of matching items of each alternative material number and the professional term;
and taking the candidate material number with the maximum number of matching items with the professional term as a target material number.
10. The apparatus according to claim 6, wherein the word segmentation unit is specifically configured to:
customizing a word segmentation device dictionary according to the professional terms of the material name and the specification model;
and utilizing the word segmentation device to segment words of the character information to obtain a target key word group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529667.2A CN112559710A (en) | 2020-12-22 | 2020-12-22 | Material information query method and query device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529667.2A CN112559710A (en) | 2020-12-22 | 2020-12-22 | Material information query method and query device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112559710A true CN112559710A (en) | 2021-03-26 |
Family
ID=75030812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011529667.2A Pending CN112559710A (en) | 2020-12-22 | 2020-12-22 | Material information query method and query device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112559710A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867511A (en) * | 2011-07-04 | 2013-01-09 | 余喆 | Method and device for recognizing natural speech |
| CN106021531A (en) * | 2016-05-25 | 2016-10-12 | 北京云知声信息技术有限公司 | Method, system and device for book inquiry through voice |
| CN109817217A (en) * | 2019-01-17 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Self-service based on speech recognition peddles method, apparatus, equipment and medium |
| CN111597219A (en) * | 2020-05-22 | 2020-08-28 | 安徽机器猫电子商务股份有限公司 | Searching method and system based on relationship attribute |
-
2020
- 2020-12-22 CN CN202011529667.2A patent/CN112559710A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867511A (en) * | 2011-07-04 | 2013-01-09 | 余喆 | Method and device for recognizing natural speech |
| CN106021531A (en) * | 2016-05-25 | 2016-10-12 | 北京云知声信息技术有限公司 | Method, system and device for book inquiry through voice |
| CN109817217A (en) * | 2019-01-17 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Self-service based on speech recognition peddles method, apparatus, equipment and medium |
| CN111597219A (en) * | 2020-05-22 | 2020-08-28 | 安徽机器猫电子商务股份有限公司 | Searching method and system based on relationship attribute |
Non-Patent Citations (1)
| Title |
|---|
| NO NAME: "《https://www.leiphone.com/category/ai/iQfSlbSzrC3bHms6.html》", 5 August 2016 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107704453B (en) | Character semantic analysis method, character semantic analysis terminal and storage medium | |
| US7415409B2 (en) | Method to train the language model of a speech recognition system to convert and index voicemails on a search engine | |
| CN108287911B (en) | Relation extraction method based on constrained remote supervision | |
| CN104199965A (en) | Semantic information retrieval method | |
| CN108027814B (en) | Stop word recognition method and device | |
| CN101019121A (en) | Method and system for indexing and retrieving document stored in database | |
| CN102207948A (en) | Method for generating incident statement sentence material base | |
| CN101794307A (en) | Vehicle navigation POI (Point of Interest) search engine based on internetwork word segmentation idea | |
| CN109147793B (en) | Voice data processing method, device and system | |
| CN110297880B (en) | Corpus product recommendation method, apparatus, device and storage medium | |
| CN111125086B (en) | Method, device, storage medium and processor for acquiring data resources | |
| CN108536807B (en) | Information processing method and device | |
| CN110321549B (en) | New concept mining method based on sequential learning, relation mining and time sequence analysis | |
| CN102081634A (en) | Speech retrieval device and method | |
| CN112445894A (en) | Business intelligent system based on artificial intelligence and analysis method thereof | |
| CN114492470A (en) | Commodity title text translation method and device, equipment, medium and product thereof | |
| CN114266256A (en) | Method and system for extracting new words in field | |
| CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
| CN101102351A (en) | Method for querying first spelling character key at visual terminal | |
| CN111666425A (en) | Automobile accessory searching method based on semantic knowledge | |
| CN110674276A (en) | Robot self-learning method, robot terminal, device and readable storage medium | |
| CN116628173B (en) | Intelligent customer service information generation system and method based on keyword extraction | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN112382276A (en) | Power grid material information acquisition method and device based on voice semantic recognition | |
| CN112182019A (en) | Semantic parsing search method for power grid statistics professional index feature extraction |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210326 |