CN110096703A - Data processing method and device, server, client for intention assessment - Google Patents
Data processing method and device, server, client for intention assessment Download PDFInfo
- Publication number
- CN110096703A CN110096703A CN201910345116.1A CN201910345116A CN110096703A CN 110096703 A CN110096703 A CN 110096703A CN 201910345116 A CN201910345116 A CN 201910345116A CN 110096703 A CN110096703 A CN 110096703A
- Authority
- CN
- China
- Prior art keywords
- clause
- intended
- intention
- user
- label
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
This application discloses a kind of data processing method for intention assessment and device, server, clients.This method includes identifying the entity and label in input text in analysis layer；The clause being consistent according to default template matching with the entity and the label；Identify that at least one user in the clause is intended to；And the analysis report that output is intended to the user.Present application addresses the ineffective technical problems of the processing mode for user's intention assessment.It is intended to by the application identification user and marking is cooperated to obtain more accurate semantic understanding result.
Description
Technical field
This application involves natural language processing fields, in particular to a kind of data processing side for intention assessment
Method and device.
Background technique
Intention assessment refers to and understands to obtain the intention of user according to the text content analysis of user's input.
Inventors have found that semantic precisely reason can be carried out for what operation personnel used at present according to intention assessment result by lacking
The service of solution and extension.
For the ineffective problem of the processing mode in the related technology for user's intention assessment, not yet propose have at present
The solution of effect.
Summary of the invention
The main purpose of the application is to provide a kind of data processing method and device for intention assessment, with solution pair
In the ineffective problem of the processing mode of user's intention assessment.
To achieve the goals above, it according to the one aspect of the application, provides at a kind of data for intention assessment
Reason method.
The data processing method for intention assessment according to the application includes: to identify the reality in input text in analysis layer
Body and label；The clause being consistent according to default template matching with the entity and the label；It identifies in the clause at least
One user is intended to；And the analysis report that output is intended to the user.
It further, include: in default mould according to the clause that default template matching is consistent with the entity and the label
Outgoing label is matched in plate；Entity is matched in default template；Judge to template set belonging to the label and the entity
In whether have the clause being consistent；If it is determined that being to have the sentence being consistent in the label and template set belonging to the entity
Formula, then matching obtains the clause being intended to for showing user.
Further, identifying that at least one user in the clause is intended to includes: user's meaning in the identification clause
Whether figure belongs to default scene；If identifying that the user in the clause is intended to belong to default scene, described be intended to is generated
The fractional weight occurred in the default scene and the description to the intention.
Further, identifying that at least one user in the clause is intended to includes: multiple use in the identification clause
Family is intended to and judges whether the intention is identical；If identifying that multiple users in the clause are intended to and judge the intention phase
Together, then the probability for being intended to occur in the scene is generated；If identifying that multiple users in the clause are intended to and judge institute
It states and is intended to not identical, then generate the score of the different intentions.
To achieve the goals above, it according to the another aspect of the application, provides at a kind of data for intention assessment
Manage device.
The data processing equipment for intention assessment according to the application includes: input analysis module, in analysis layer
Entity and label in identification input text；Matching module, for according to default template matching and the entity and the label
The clause being consistent；Identification module, at least one user in the clause is intended to for identification；And it is intended to output module, it is defeated
The analysis report that the user is intended to out.
Further, the matching module includes: the first matching unit, for matching outgoing label in default template；The
Two matching units, for matching entity in default template；Judging unit, for judging to the label and entity institute
It is to have the clause being consistent in the template set of category；It is intended to matching unit, for if it is determined that the label and entity institute
It is to have the clause being consistent in the template set of category, then matching obtains the clause being intended to for showing user.
Further, the identification module includes: recognition unit, and whether the user in the clause is intended to belong to for identification
In default scene；Generation unit, if generating the meaning for identifying that the user in the clause is intended to belong to default scene
The fractional weight that figure occurs in the default scene and the description to the intention.
Further, the identification module includes: identical intention assessment unit, for identification multiple use in the clause
Family is intended to and judges whether the intention is identical；Probability unit, if for identifying that multiple users in the clause are intended to simultaneously
Judge that the intention is identical, then generates the probability for being intended to occur in the scene；Marking unit, if for identifying the sentence
Multiple users in formula are intended to and judge that the intention is not identical, then generate the score of the different intentions.
To achieve the goals above, according to the another aspect of the application, a kind of client is provided, comprising: for executing
The data processing method stated.
To achieve the goals above, according to the application's in another aspect, providing a kind of server, comprising: the number
According to processing unit.
It is used for the data processing method and device of intention assessment in the embodiment of the present application, is inputted using being identified in analysis layer
The mode of entity and label in text presets the clause that template matching is consistent with the entity and the label by basis,
Achieve the purpose that the analysis report that at least one user in the identification clause is intended to and output is intended to the user, from
And the semantic technical effect for precisely understanding and extending in intention assessment is realized, and then solve the place for user's intention assessment
The ineffective technical problem of reason mode.
Detailed description of the invention
The attached drawing constituted part of this application is used to provide further understanding of the present application, so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Constitute the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the data processing method flow diagram for intention assessment according to the application first embodiment；
Fig. 2 is the data processing method flow diagram for intention assessment according to the application second embodiment；
Fig. 3 is the data processing method flow diagram for intention assessment according to the application 3rd embodiment；
Fig. 4 is the data processing method flow diagram for intention assessment according to the application fourth embodiment；
Fig. 5 is the data processing equipment structural diagram for intention assessment according to the application first embodiment；
Fig. 6 is the data processing equipment structural diagram for intention assessment according to the application second embodiment；
Fig. 7 is the data processing equipment structural diagram for intention assessment according to the application 3rd embodiment；
Fig. 8 is the data processing method flow diagram for intention assessment according to the application fourth embodiment.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
In this application, term " on ", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on the figure or
Positional relationship.These terms are not intended to limit indicated dress primarily to better describe the application and embodiment
Set, element or component must have particular orientation, or constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term " on " also are likely used for indicating certain relations of dependence or connection relationship in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in this application can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction；It can be mechanical connection, or electrical connection；It can be direct phase
It even, or indirectly connected through an intermediary, or is two connections internal between device, element or component.
For those of ordinary skills, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, this method includes the following steps, namely S102 to step S108:
Step S102 identifies the entity and label in input text in analysis layer；
Meaning by analyzing entity and label in the input text in the analysis layer, as the input text
Scheme the basic condition of identification.The entity refers to the entity information that occurs in input text, for example, story title, city name,
Person names etc..The label refers to the content for belonging to a category information occurred in input text, can be variable or invariant.
For example, time tag, album label, song label etc..
Step S104, the clause being consistent according to default template matching with the entity and the label；
The clause being consistent with the entity and the label can be matched according to the default template, in the default mould
It may include what a variety of clause formed in plate.It can after clause and the default template matching that the entity and the label are consistent
To determine to be intended to affiliated clause.
Step S106 identifies that at least one user in the clause is intended to；
By identifying that at least one user of the clause is intended to, intention assessment is carried out according to the clause matched.
It should be noted that the user that a completion is included at least in the clause is intended to, it can also include multiple use
Family is intended to, in embodiments herein and without specifically limiting, as long as can satisfy clause carries out user's intention assessment
It is required that.
Step S108 exports the analysis report being intended to the user.
The analysis report being intended to the user is exported according to the intention assessment result, includes in the analysis report
Scores are intended to for different in the clause that matches.
It should be noted that the analysis exported in the analysis report being intended to the user including a variety of intentions is given a mark
As a result, and weight of giving a mark can be to be pre-configured in embodiments herein and without specifically limiting.
It can be seen from the above description that the application realizes following technical effect:
In the embodiment of the present application, using by the way of the entity and label that analysis layer identifies in input text, pass through root
According to the clause that default template matching is consistent with the entity and the label, at least one of described clause of identification use is reached
The purpose of analysis report that family is intended to and output is intended to the user, thus realize in intention assessment it is semantic precisely understand with
The technical effect of extension, and then solve the technical problem ineffective for the processing mode of user's intention assessment.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in Fig. 2, according to default template matching and institute
Stating the clause that entity is consistent with the label includes:
Step S202 matches outgoing label in default template；
By matching outgoing label in the default template, the label may include it is multiple, pass through the default template
In include multiple groups clause, tag match can be carried out.
Step S204 matches entity in default template；
By matching entity in the default template, the entity may include it is multiple, pass through the default template
In include multiple groups clause, Entities Matching can be carried out.
Step S206 judges whether there is the clause being consistent in the label and template set belonging to the entity；
Judge whether there is the clause being consistent in the label and the template set of the template belonging to the entity.Institute
Stating clause includes label and the entity.
Step S208, if it is determined that being to have the clause being consistent in the label and template set belonging to the entity,
Then matching obtains the clause being intended to for showing user.
If it is determined that can then be matched to being to have the clause being consistent in the label and template set belonging to the entity
Obtain the clause being intended to for showing user.The label is minimum unit, and the entity is identical as the rank of label, the mould
Plate includes label or also may include entity.Include at least one template in the clause or combined by multiple template and
At.At least one described clause can correspond to the intention of user or an intention of multiple clause and the user
It is corresponding.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 3, identifying in the clause at least
One user is intended to
Step S302 identifies that the user in the clause is intended to whether belong to default scene；
Identify that the user in the clause is intended to whether belong to preset scene, default scene is obtained by being pre-configured with
, can be target problem inquiry intention scene, dialogue intention scene, be intended to handoff scenario etc..
Step S304 generates the intention in institute if identifying that the user in the clause is intended to belong to default scene
State the fractional weight occurred in default scene and the description to the intention.
If identifying that the user in the clause is intended to belong to default scene, the intention is generated in the default scene
The fractional weight of middle appearance and description to the intention.When user is intended to belong to the default scene, generating the intention can
The fractional weight in the default scene and the description to the intention can be belonged to.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 4, identifying in the clause at least
One user is intended to
Step S402 identifies that multiple users in the clause are intended to and judge whether the intention is identical；
It identifies that multiple users in the clause are intended to, and judges that multiple users are intended to whether belong to identical meaning
Figure.
Step S404 generates institute if identifying that multiple users in the clause are intended to and judge that the intention is identical
State the probability for being intended to occur in the scene；
If identify that multiple users in the clause are intended to and judge that the intention is identical, the intention is generated
The probability occurred in the scene.For example, being then somebody's turn to do when being intended to by multiple users in clause and judging that the intention is identical
Being intended to the probability occurred in the scene is 60%.
Step S406 is generated if identifying that multiple users in the clause are intended to and judge that the intention is not identical
The score of the different intentions.
If identify that multiple users in the clause are intended to and judge that the intention is not identical, different institutes are generated
State the score of intention.For example, be intended to by the multiple users identified in the clause and judge that the intention is not identical, then it is right
The marking result of the intention should be generated.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
According to the embodiment of the present application, additionally provide a kind of for implementing the data processing for intention assessment of the above method
Device, as shown in figure 5, the device includes: input analysis module 10, for identifying entity and mark in input text in analysis layer
Label；Matching module 20, the clause for being consistent according to template matching is preset with the entity and the label；Identification module 30,
At least one user in the clause is intended to for identification；And it is intended to output module 40, what output was intended to the user
Analysis report.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in fig. 6, the matching module 20 includes:
One matching unit 201, for matching outgoing label in default template；Second matching unit 202, for being matched in default template
Entity out；Judging unit 203, for judging to being to have the sentence being consistent in the label and template set belonging to the entity
Formula；It is intended to matching unit 204, for if it is determined that being consistent to having in the label and template set belonging to the entity
Clause, then matching obtains the clause being intended to for showing user.
By being analyzed in the analysis layer in the input text in first matching unit 201 of the embodiment of the present application
Entity and label, the basic condition of the intention assessment as the input text.The entity refers to be occurred in input text
Entity information, for example, story title, city name, person names etc..The label refers to that is occurred in input text belongs to one
The content of category information can be variable or invariant.For example, time tag, album label, song label etc..
In second matching unit 202 of the embodiment of the present application according to the default template can match with the entity and
The clause that the label is consistent may include what a variety of clause formed in the default template.The entity and the label
It can determine to be intended to affiliated clause after the clause and the default template matching that are consistent.
By identifying that at least one user of the clause is intended in the judging unit 203 of the embodiment of the present application, according to
The clause mixed carries out intention assessment.
It should be noted that the user that a completion is included at least in the clause is intended to, it can also include multiple use
Family is intended to, in embodiments herein and without specifically limiting, as long as can satisfy clause carries out user's intention assessment
It is required that.
It is exported in the intention matching unit 204 of the embodiment of the present application according to the intention assessment result and the user is intended to
Analysis report, include that scores are intended to for different in the clause that matches in the analysis report.
It should be noted that the analysis exported in the analysis report being intended to the user including a variety of intentions is given a mark
As a result, and weight of giving a mark can be to be pre-configured in embodiments herein and without specifically limiting.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in fig. 7, the identification module includes: identification
Unit 301, the user in the clause is intended to whether belong to default scene for identification；Generation unit 302, if for identifying
User in the clause is intended to belong to default scene, then generates the fractional weight for being intended to occur in the default scene
With the description to the intention.
Identify that the user in the clause is intended to whether belong to preset field in the recognition unit 301 of the embodiment of the present application
Scape, default scene can be target problem inquiry intention scene, dialogue is intended to scene, is intended to switching by being pre-configured with acquisition
Scene etc..
If identifying that the user in the clause is intended to belong to default scene in the generation unit 302 of the embodiment of the present application,
Then generate the fractional weight for being intended to occur in the default scene and the description to the intention.User is intended to belong to institute
When stating default scene, the fractional weight that the intention may belong in the default scene and the description to the intention are generated.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 8, the identification module includes: identical
Intention assessment unit 303, multiple users in the clause are intended to and judge whether the intention is identical for identification；Probability list
Member 304 generates the intention and exists if multiple users for identifying in the clause are intended to and judge that the intention is identical
The probability occurred in scene；Marking unit 305, if multiple users for identifying in the clause are intended to and judge the meaning
Figure is not identical, then generates the score of the different intentions.
It identifies that multiple users in the clause are intended in the identical intention assessment unit 303 of the embodiment of the present application, and sentences
Multiple users of breaking are intended to whether belong to identical intention.
If identifying that multiple users in the clause are intended to and judge institute in the probability unit 304 of the embodiment of the present application
It states when being intended to identical, then generates and described be intended to the probability that occurs in the scene.For example, being intended to simultaneously by multiple users in clause
When judging that the intention is identical, then obtaining the probability that the intention occurs in the scene is 60%.
If identifying that multiple users in the clause are intended to and judge institute in the marking unit 305 of the embodiment of the present application
It states when being intended to not identical, then generates the score of the different intentions.For example, by identifying that multiple users in the clause anticipate
Scheme and judge that the intention is not identical, then the corresponding marking result for generating the intention.
In another embodiment of the application, a kind of client is additionally provided, comprising: for executing the data processing
Method.The realization principle and beneficial effect of the data processing method as described above, no longer repeated herein.
In the another embodiment of the application, a kind of server is additionally provided, comprising: the data processing equipment.Institute
The realization principle and beneficial effect for stating data processing equipment as described above, no longer repeated herein.
Obviously, those skilled in the art should be understood that each module of above-mentioned the application or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the application be not limited to it is any specific
Hardware and software combines.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.
Claims (10)
1. a kind of data processing method for intention assessment characterized by comprising
The entity and label in input text are identified in analysis layer；
The clause being consistent according to default template matching with the entity and the label；
Identify that at least one user in the clause is intended to；And
Export the analysis report being intended to the user.
2. data processing method according to claim 1, which is characterized in that according to default template matching and the entity and
The clause that the label is consistent includes:
Outgoing label is matched in default template；
Entity is matched in default template；
Judge whether there is the clause being consistent in the label and template set belonging to the entity；
If it is determined that then matching is used for being to have the clause being consistent in the label and template set belonging to the entity
Show the clause that user is intended to.
3. data processing method according to claim 1, which is characterized in that identify at least one user in the clause
Intention includes:
Identify that the user in the clause is intended to whether belong to default scene；
If identifying that the user in the clause is intended to belong to default scene, generates the intention and go out in the default scene
Existing fractional weight and the description to the intention.
4. data processing method according to claim 1, which is characterized in that identify at least one user in the clause
Intention includes:
Identify that multiple users in the clause are intended to and judge whether the intention is identical；
If identifying that multiple users in the clause are intended to and judge that the intention is identical, the intention is generated in the scene
The probability of appearance；
If identifying that multiple users in the clause are intended to and judge that the intention is not identical, the different intentions are generated
Score.
5. a kind of data processing equipment for intention assessment characterized by comprising
Analysis module is inputted, for identifying entity and label in input text in analysis layer；
Matching module, the clause for being consistent according to template matching is preset with the entity and the label；
Identification module, at least one user in the clause is intended to for identification；And
It is intended to output module, exports the analysis report being intended to the user.
6. data processing equipment according to claim 5, which is characterized in that the matching module includes:
First matching unit, for matching outgoing label in default template；
Second matching unit, for matching entity in default template；
Judging unit, for judging to being to have the clause being consistent in the label and template set belonging to the entity；
It is intended to matching unit, for if it is determined that being to have the sentence being consistent in the label and template set belonging to the entity
Formula, then matching obtains the clause being intended to for showing user.
7. data processing equipment according to claim 5, which is characterized in that the identification module includes:
Recognition unit, the user in the clause is intended to whether belong to default scene for identification；
Generation unit, if generating the intention in institute for identifying that the user in the clause is intended to belong to default scene
State the fractional weight occurred in default scene and the description to the intention.
8. data processing equipment according to claim 5, which is characterized in that the identification module includes:
Identical intention assessment unit, multiple users in the clause are intended to and judge whether the intention is identical for identification；
Probability unit generates institute if multiple users for identifying in the clause are intended to and judge that the intention is identical
State the probability for being intended to occur in the scene；
Unit of giving a mark generates if multiple users for identifying in the clause are intended to and judge that the intention is not identical
The score of the different intentions.
9. a kind of client characterized by comprising for executing such as the described in any item data processing sides of Claims 1-4
Method.
10. a kind of server characterized by comprising such as the described in any item data processing equipments of claim 5 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345116.1A CN110096703B (en) | 2019-04-26 | 2019-04-26 | Data processing method and device for intention recognition, server and client |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910345116.1A CN110096703B (en) | 2019-04-26 | 2019-04-26 | Data processing method and device for intention recognition, server and client |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110096703A true CN110096703A (en) | 2019-08-06 |
| CN110096703B CN110096703B (en) | 2023-10-31 |
Family
ID=67446072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910345116.1A Active CN110096703B (en) | 2019-04-26 | 2019-04-26 | Data processing method and device for intention recognition, server and client |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096703B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674259A (en) * | 2019-09-27 | 2020-01-10 | 北京百度网讯科技有限公司 | Intention understanding method and device |
| CN113010768A (en) * | 2019-12-19 | 2021-06-22 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
| CN114629813A (en) * | 2021-12-30 | 2022-06-14 | 亚信科技（中国）有限公司 | Intention report reporting method and device, electronic equipment, storage medium and product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108509412A (en) * | 2018-03-02 | 2018-09-07 | 北京搜狗科技发展有限公司 | A kind of data processing method, device, electronic equipment and storage medium |
| CN108628830A (en) * | 2018-04-24 | 2018-10-09 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of semantics recognition |
| CN108874917A (en) * | 2018-05-30 | 2018-11-23 | 北京五八信息技术有限公司 | Intension recognizing method, device, equipment and storage medium |
| CN109508423A (en) * | 2018-12-14 | 2019-03-22 | 平安科技（深圳）有限公司 | Source of houses recommended method, device, equipment and storage medium based on semantics recognition |
-
2019
- 2019-04-26 CN CN201910345116.1A patent/CN110096703B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108509412A (en) * | 2018-03-02 | 2018-09-07 | 北京搜狗科技发展有限公司 | A kind of data processing method, device, electronic equipment and storage medium |
| CN108628830A (en) * | 2018-04-24 | 2018-10-09 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of semantics recognition |
| CN108874917A (en) * | 2018-05-30 | 2018-11-23 | 北京五八信息技术有限公司 | Intension recognizing method, device, equipment and storage medium |
| CN109508423A (en) * | 2018-12-14 | 2019-03-22 | 平安科技（深圳）有限公司 | Source of houses recommended method, device, equipment and storage medium based on semantics recognition |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674259A (en) * | 2019-09-27 | 2020-01-10 | 北京百度网讯科技有限公司 | Intention understanding method and device |
| CN113010768A (en) * | 2019-12-19 | 2021-06-22 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
| CN113010768B (en) * | 2019-12-19 | 2024-03-19 | 北京搜狗科技发展有限公司 | Data processing method and device for data processing |
| CN114629813A (en) * | 2021-12-30 | 2022-06-14 | 亚信科技（中国）有限公司 | Intention report reporting method and device, electronic equipment, storage medium and product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110096703B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102693272B (en) | Keyword extraction from uniform resource locators (URLs) | |
| CN106776544A (en) | Character relation recognition methods and device and segmenting method | |
| CN102955781B (en) | A kind of personage's searching method and device | |
| CN110096703A (en) | Data processing method and device, server, client for intention assessment | |
| CN110147437A (en) | A kind of searching method and device of knowledge based map | |
| CN109002516A (en) | A kind of searching method and device | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| US20060074902A1 (en) | Forming intent-based clusters and employing same by search | |
| US20210406473A1 (en) | System and method for building chatbot providing intelligent conversational service | |
| CN110866093A (en) | Machine question-answering method and device | |
| KR20160136442A (en) | Computer generated natural language outputs in question answer systems | |
| CN112650858B (en) | Emergency assistance information acquisition method and device, computer equipment and medium | |
| CN104699737A (en) | Method and system for managing a search | |
| CN110929125A (en) | Search recall method, apparatus, device and storage medium thereof | |
| CN110852095B (en) | Statement hot spot extraction method and system | |
| CN106815356A (en) | Precision target user message method for pushing and system based on semantic analysis | |
| CN110019712A (en) | More intent query method and apparatus, computer equipment and computer readable storage medium | |
| CN104239570B (en) | The searching method and device of paper | |
| CN110162675B (en) | Method and device for generating answer sentence, computer readable medium and electronic device | |
| CN111966781B (en) | Interaction method and device for data query, electronic equipment and storage medium | |
| US20130318098A1 (en) | Method and system to analyze email addresses | |
| CN112035599A (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN109918627A (en) | Document creation method, device, electronic equipment and storage medium | |
| CN109710739A (en) | A kind of information processing method and device, storage medium | |
| CN113986968B (en) | Scheme intelligent proofreading method based on electric power standard standardization datamation |
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 |