CN110020191A - Electronic device, the target object invited outside investment determine method and storage medium - Google Patents
Electronic device, the target object invited outside investment determine method and storage medium Download PDFInfo
- Publication number
- CN110020191A CN110020191A CN201810798138.9A CN201810798138A CN110020191A CN 110020191 A CN110020191 A CN 110020191A CN 201810798138 A CN201810798138 A CN 201810798138A CN 110020191 A CN110020191 A CN 110020191A
- Authority
- CN
- China
- Prior art keywords
- key message
- project
- target object
- outside investment
- test
- 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
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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of electronic device, the target objects invited outside investment to determine method and storage medium, which comprises obtains the first key message in the text information of predetermined project of inviting outside investment；The second key message of each enterprise for project of inviting outside investment described in participating in is obtained, the second key message of each enterprise that will acquire respectively is matched with first key message, to obtain the matching degree of each enterprise Yu the project of inviting outside investment；It determines that the enterprise is the target object invited outside investment, according to predetermined target object classification method, target object grade classification is carried out to the enterprise；Determine whether the rank of the enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.A large amount of human cost of inviting outside investment, save can be completed by intelligent means, and improves the accuracy of result.
Description
Technical field
The present invention relates to the field of inviting outside investment more particularly to a kind of electronic devices, the target object determination side to invite outside investment
Method and storage medium.
Background technique
With the development of computer technology and intelligent information, many fields are handled numerous to substitute using machine intelligenceization
Trivial manual procedure can not only save human resources, reduce cost, and can a accuracy rate and stabilization for improving work
Property.But at present in the field of inviting outside investment, interpretation of the staff to relevant policies is still depended primarily on, and will interpret
Policy later is manually matched and is screened with the public information of enterprise, and efficient intelligent means are lacked, and waste is a large amount of
Human cost, and not can guarantee the accuracy of result.
Summary of the invention
In view of this, the present invention propose a kind of electronic device, the electronic device include memory and with the memory
The processor of connection, the processor determine program for executing the target object invited outside investment stored on the memory,
The target object invited outside investment, which determines, realizes following steps when program is executed by the processor:
A1, the first key message in the text information of predetermined project of inviting outside investment is obtained；
Second key message of each enterprise for project of inviting outside investment described in A2, acquisition participation, each enterprise that will acquire respectively
The second key message matched with first key message, to obtain of each enterprise Yu the project of inviting outside investment
With degree；
If A3, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, really
The fixed enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target to the enterprise
Object grade classification；
Mapping relations between A4, target object rank according to the pre-stored data and target object of inviting outside investment, determining should
Whether the rank of enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
Preferably, the step A1 includes:
According to the first key message marking model that preparatory training is completed, to the text of predetermined project of inviting outside investment
Information is analyzed, to obtain the first key message in text information.
Preferably, it is described it is preparatory training complete the first key message marking model be neural network model, described first
The training process of key message marking model includes the following steps:
E1, obtain preset quantity the project of inviting outside investment for having marked key message text information sample and each text
The corresponding urtext information of this message sample；
F1, the training subset that the corresponding urtext information of the text information sample of each project is divided into the first ratio and
The test subset of second ratio；
G1, it is marked using urtext information training first key message of each project in the training subset
Model, to obtain trained key message marking model；
H1, mould is marked to first key message using the urtext information of each project in the test subset
Type is tested, if test passes through, training terminates, alternatively, increasing the text envelope of the training subset if test does not pass through
It ceases the quantity of sample and re-executes above-mentioned steps E1, F1, G1 and H1.
Preferably, in the step H1, the urtext information using each project in the test subset
The step of testing the first key message marking model include:
Utilize trained first key message mark then original of the model to each project in the test subset
Beginning text information is labeled, with obtain each project by manually carry out the third key message that marks of key message with
The equal probability value of the 4th key message that key message marks is carried out automatically by the first key message marking model；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described
Preset probability threshold value then carries out model accuracy test for the project, which is carried out artificial mark key message, with
It obtains the corresponding third key message of the project, and calls the first key message marking model automatic marking project, to obtain
Corresponding 4th key message of the project；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that tested for the model accuracy of the project
Result be correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that be directed to the project
Model accuracy test result be mistake；
It is greater than if the percentage that correct model accuracy test result accounts for all model accuracy test results default
Percentage threshold, it is determined that the test of the first key message marking model is passed through, alternatively, accurate if correct model
Property test result account for all model accuracy test results percentage be less than or equal to preset percentage threshold value, it is determined that it is right
The test of the first key message marking model does not pass through.
Preferably, in the step A3, the predetermined target object classification method is density clustering
Algorithm, the density-based algorithms are DBscan algorithm.
In addition, to achieve the above object, the present invention also proposes that a kind of target object invited outside investment determines method, feature
It is, described method includes following steps:
S1, the first key message in the text information of predetermined project of inviting outside investment is obtained；
Second key message of each enterprise for project of inviting outside investment described in S2, acquisition participation, each enterprise that will acquire respectively
The second key message matched with first key message, to obtain of each enterprise Yu the project of inviting outside investment
With degree；
If S3, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, really
The fixed enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target to the enterprise
Object grade classification；
Mapping relations between S4, target object rank according to the pre-stored data and target object of inviting outside investment, determining should
Whether the rank of enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
Preferably, the step S1 includes:
According to the first key message marking model that preparatory training is completed, to the text of predetermined project of inviting outside investment
Information is analyzed, to obtain the first key message in text information.
Preferably, it is described it is preparatory training complete the first key message marking model be neural network model, described first
The training process of key message marking model includes the following steps:
E2, obtain preset quantity the project of inviting outside investment for having marked key message text information sample and each text
The corresponding urtext information of this message sample；
F2, the training subset that the corresponding urtext information of the text information sample of each project is divided into the first ratio and
The test subset of second ratio；
G2, it is marked using urtext information training first key message of each project in the training subset
Model, to obtain trained key message marking model；
H2, mould is marked to first key message using the urtext information of each project in the test subset
Type is tested, if test passes through, training terminates, alternatively, increasing the text envelope of the training subset if test does not pass through
It ceases the quantity of sample and re-executes above-mentioned steps E2, F2, G2 and H2.
Preferably, in the step H2, the urtext information using each project in the test subset
The step of testing the first key message marking model include:
Utilize trained first key message mark then original of the model to each project in the test subset
Beginning text information is labeled, with obtain each project by manually carry out the third key message that marks of key message with
The equal probability value of the 4th key message that key message marks is carried out automatically by the first key message marking model；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described
Preset probability threshold value then carries out model accuracy test for the project, which is carried out artificial mark key message, with
It obtains the corresponding third key message of the project, and calls the first key message marking model automatic marking project, to obtain
Corresponding 4th key message of the project；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that tested for the model accuracy of the project
Result be correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that be directed to the project
Model accuracy test result be mistake；
It is greater than if the percentage that correct model accuracy test result accounts for all model accuracy test results default
Percentage threshold, it is determined that the test of the first key message marking model is passed through, alternatively, accurate if correct model
Property test result account for all model accuracy test results percentage be less than or equal to preset percentage threshold value, it is determined that it is right
The test of the first key message marking model does not pass through.
In addition, to achieve the above object, the present invention also proposes a kind of computer readable storage medium, described computer-readable
Storage medium is stored with the target object invited outside investment and determines program, and the target object invited outside investment determines that program can be by extremely
A few processor executes, so that at least one described processor executes the target object determination side to invite outside investment as described above
The step of method.
Electronic device proposed by the invention, the target object invited outside investment determine method and storage medium, pass through first
Obtain the first key message in the text information of predetermined project of inviting outside investment；Then it obtains and participates in the trade and investment promotion
Second key message of each enterprise for project of bringing in funds, the second key message of each enterprise that will acquire respectively and first key
Information is matched, to obtain the matching degree of each enterprise Yu the project of inviting outside investment；If having enterprise and the trade and investment promotion again
The matching degree for project of bringing in funds is greater than predefined matching degree reference threshold, it is determined that and the enterprise is the target object invited outside investment,
According to predetermined target object classification method, target object grade classification is carried out to the enterprise；Last basis is stored in advance
Target object rank and target object of inviting outside investment between mapping relations, determine whether the rank of the enterprise meets trade and investment promotion and draw
The rank of money project, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.It can complete to promote trade and investment by intelligent means and draw
It provides, save a large amount of human cost, and improve the accuracy of result.
Detailed description of the invention
Fig. 1 is the schematic diagram of the optional hardware structure of electronic device one proposed by the present invention；
Fig. 2 is the program module signal that the target object invited outside investment in one embodiment of electronic device of the present invention determines program
Figure；
Fig. 3 is the implementation flow chart that the target object that the present invention invites outside investment determines method preferred embodiment.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as its relative importance of indication or suggestion or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection scope within.
As shown in fig.1, being the optional hardware structure schematic diagram of electronic device one proposed by the present invention.In the present embodiment,
Electronic device 10 may include, but be not limited only to, and connection memory 11, processor 12, net can be in communication with each other by communication bus 14
Network interface 13.It should be pointed out that Fig. 1 illustrates only the electronic device 10 with component 11-14, it should be understood that simultaneously
All components shown realistic are not applied, the implementation that can be substituted is more or less component.
Wherein, memory 11 includes at least a type of computer readable storage medium, computer readable storage medium
Including flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device (RAM), quiet
State random access storage device (SRAM), electrically erasable programmable read-only memory (EEPROM), can be compiled read-only memory (ROM)
Journey read-only memory (PROM), magnetic storage, disk, CD etc..In some embodiments, memory 11 can be electronics dress
Set 10 internal storage unit, such as the hard disk or memory of electronic device 10.In further embodiments, memory 11 can also be with
It is the outer packet storage device of electronic device 10, such as the plug-in type hard disk being equipped on electronic device 10, intelligent memory card (Smart
Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Certainly, it stores
Device 11 can also both including electronic device 10 internal storage unit and also including its outer packet storage device.In the present embodiment, storage
Device 11 is installed on the operating system and types of applications software of electronic device 10, such as the target pair invited outside investment commonly used in storage
As determining program etc..In addition, memory 11 can be also used for temporarily storing the Various types of data that has exported or will export.
Processor 12 can be in some embodiments central processing unit (Central Processing Unit, CPU),
Controller, microcontroller, microprocessor or other data processing chips.Processor 12 is commonly used in control electronic device 10
Overall operation.In the present embodiment, program code or processing data of the processor 12 for being stored in run memory 11, such as
The target object of operation invited outside investment determines program etc..
Network interface 13 may include radio network interface or wired network interface, and network interface 13 is commonly used in filling in electronics
It sets and establishes communication connection between 10 and other electronic equipments.
Communication bus 14 is for realizing the communication connection between component 11-13.
Fig. 1 illustrates only the electronic device 10 that program is determined with component 11-14 and the target object invited outside investment, but
Be it should be understood that, it is not required that implement all components shown, the implementation that can be substituted is more or less component.
Optionally, electronic device 10 can also include user interface (not shown in figure 1), and user interface may include display
Device, input unit such as keyboard, wherein user interface can also be including standard wireline interface and wireless interface etc..
Optionally, in some embodiments, display can be light-emitting diode display, liquid crystal display, touch control type LCD and show
Device and OLED touch device etc..Further, display is alternatively referred to as display screen or display unit, for being shown in electronic device
Information is handled in 10 and for showing visual user interface.
Optionally, in some embodiments, electronic device 10 can also include that audio unit (does not show in audio unit Fig. 1
Out), audio unit can be in call signal reception pattern, call mode, logging mode, speech recognition mould in electronic device 10
When under the isotypes such as formula, broadcast reception mode, received or storage audio data is converted into audio signal；Further
Ground, electronic device 10 can also include audio output unit, and the audio signal that audio output unit converts audio unit exports,
And audio output unit can also provide the relevant audio output of specific function that executes to electronic device 10 (such as calling is believed
Number receive sound, message sink sound etc.), audio output unit may include loudspeaker, buzzer etc..
Optionally, in some embodiments, electronic device 10 can also include alarm unit (not shown), alarm list
Member can provide output and the generation of event is notified electron device 10.Typical event may include calling reception, message
Reception, key signals input, touch input etc..Other than audio or video export, alarm unit can be with different sides
Formula provides output with the generation of notification event.For example, alarm unit can provide output in the form of vibration, exhaled when receiving
Cry, message or it is some other can make electronic device 10 enter communication pattern when, alarm unit can provide tactile output (that is,
Vibration) to notify to user.
In one embodiment, the target object invited outside investment stored in memory 11 determines that program is executed by processor 12
When, realize following operation:
A1, the first key message in the text information of predetermined project of inviting outside investment is obtained；
Specifically, the text information of predetermined project of inviting outside investment includes the related subject invited outside investment and each master
Corresponding content information is inscribed, specifically, the text information of predetermined project of inviting outside investment can enter by given network address
Port address obtains page link, is downloaded to obtain；Further, in the present embodiment, first completed according to preparatory training
Key message marking model analyzes the text information of predetermined project of inviting outside investment, to obtain text information
In the first key message；Specifically, first key message include theme, trade classification, company information keyword such as " on
The company informations keywords such as company, city " " assets are more than 100,000,000 " " professional is no less than 50 people ", trade and investment promotion signal word are as " simultaneously
Trade and investment promotions signal word, the incentive message such as purchase ", " planning investing inside the province " etc.；
Specifically, in the present embodiment, the first key message marking model that the preparatory training is completed is neural network
Model, the pass of mark that the training process of the first key message marking model includes the following steps: E, obtains preset quantity
The text information sample of the project of inviting outside investment of key information and the corresponding urtext information of each text information sample；
F, by the corresponding urtext information of the text information sample of each project be divided into the first ratio training subset and
The test subset of second ratio；
G, it is marked using urtext information training first key message of each project in the training subset
Model, to obtain trained key message marking model；
H, mould is marked to first key message using the urtext information of each project in the test subset
Type is tested, if test passes through, training terminates, alternatively, increasing the text envelope of the training subset if test does not pass through
It ceases the quantity of sample and re-executes above-mentioned steps E, F, G and H.
Specifically, in the step H, the urtext information pair using each project in the test subset
The step of first key message marking model is tested include:
Utilize trained first key message mark then original of the model to each project in the test subset
Beginning text information is labeled, with obtain each project by manually carry out the third key message that marks of key message with
The equal probability value of the 4th key message that key message marks is carried out automatically by the first key message marking model；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described
Preset probability threshold value then carries out model accuracy test for the project, which is carried out artificial mark key message, with
It obtains the corresponding third key message of the project, and calls the first key message marking model automatic marking project, to obtain
Corresponding 4th key message of the project；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that tested for the model accuracy of the project
Result be correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that be directed to the project
Model accuracy test result be mistake；
It is greater than if the percentage that correct model accuracy test result accounts for all model accuracy test results default
Percentage threshold, it is determined that the test of the first key message marking model is passed through, alternatively, accurate if correct model
Property test result account for all model accuracy test results percentage be less than or equal to preset percentage threshold value, it is determined that it is right
The test of the first key message marking model does not pass through.
Second key message of each enterprise for project of inviting outside investment described in A2, acquisition participation, each enterprise that will acquire respectively
The second key message matched with first key message, to obtain of each enterprise Yu the project of inviting outside investment
With degree；
Specifically, can invite outside investment described in participation item according to the second key message marking model that preparatory training is completed
The text information of each enterprise of purpose carries out key message mark, to mark out corresponding second key message of each enterprise.Tool
Body, the second key message marking model is also neural network model, the training process and test process of the model
It is identical as the principle of the first key message marking model, here, being not repeated.
If A3, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, really
The fixed enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target to the enterprise
Object grade classification；
Specifically, predetermined target object classification method is density-based algorithms, in one embodiment, base
It is DBscan algorithm in the clustering algorithm of density, the specific density-based algorithms include: to be existed according to each target object
Data object information disclosed in preset time (for example, in the half a year nearest from current point in time), for example, enterprise's turnover, in
The data object informations such as target trade classification, the theme of bid target, trade and investment promotion signal word are marked, each target object are divided into default
The target object of rank, for example, listed company be the target object of first level, market value cross hundred million be second level target object,
Professional is no less than the target object of the pre-set levels such as the target object that 50 people are third level；Respectively with different pre-set levels
Different input objects of the target object as DBscan algorithm, it is to be understood that the target object institute of different pre-set levels
The classification of category is different, and different discrete datas, and default sweep radius e (example can be divided into according to the target object of pre-set level
Such as, e=3 indicates the minimum same data object Information Number that the target object of same pre-set level includes) and it is minimum comprising point
Minp (for example, minp=5, indicates target object of 5 class difference pre-set levels) is counted, then optional one not visited point
(target object of pre-set level) starts, and finds out within sweep radius e that (including e) point is accessed (to access the pre-set level
Target object) number, if the accessed number of the point is greater than or equal to minp within sweep radius e, the point is (current
The target object of pre-set level) and other numbers being accessed within sweep radius e formed more than or equal to minp times points
One cluster (cluster of a cluster), and starting point is marked as access point.Then recurrence handles the cluster in the same way
Interior all not visited points, to be extended to cluster.If the accessed number of the point is less than within sweep radius e
Minp, then the point be temporarily labeled as noise spot (non-cluster point, it is corresponding be in the present embodiment with the project of inviting outside investment not
The target object of relevant pre-set level), if cluster is fully extended, i.e., all the points in cluster are marked as having accessed, then use
Same algorithm goes to handle not visited point.Grade is carried out by the target object that this clustering method can invite outside investment
Do not classify.
Mapping relations between A4, target object rank according to the pre-stored data and target object of inviting outside investment, determining should
Whether the rank of enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
By above-mentioned thing embodiment it is found that electronic device proposed by the present invention, obtains predetermined trick by acquisition first
Quotient bring in funds project text information in the first key message；Then the of each enterprise for project of inviting outside investment described in participating in is obtained
Two key messages, the second key message of each enterprise that will acquire respectively is matched with first key message, to obtain
The matching degree of each enterprise and the project of inviting outside investment；If thering is enterprise and the matching degree of the project of inviting outside investment to be greater than again
Predefined matching degree reference threshold, it is determined that the enterprise is the target object invited outside investment, according to predetermined target pair
As classification method, target object grade classification is carried out to the enterprise；Last target object rank according to the pre-stored data and trade and investment promotion
The mapping relations brought in funds between target object, determine whether the rank of the enterprise meets the rank for the project of inviting outside investment, if satisfied,
Then it is automatically performed the recommendation for the project of inviting outside investment.Can by intelligent means complete invite outside investment, save a large amount of manpower at
This, and improve the accuracy of result.
In addition, the function that the target object invited outside investment of the invention determines that program is realized according to its each section is different,
It can be described with program module with the same function.It please refers to shown in Fig. 2, is that one embodiment of electronic device of the present invention is infected
The target object that quotient brings in funds determines the program module schematic diagram of program.In the present embodiment, the target object invited outside investment determines journey
The difference for the function that sequence is realized according to its each section can be divided into and obtain module 201, matching module 202, categorization module
203 and determining module 204.By above description it is found that the so-called program module of the present invention is to refer to complete specific function
Series of computation machine program instruction section, determine that program is filled in electronics more suitable for describing the target object invited outside investment than program
Set the implementation procedure in 10.The functions or operations step that the module 201-204 is realized is similar as above, herein no longer in detail
It states, illustratively, such as wherein:
Obtain the first key message in text information of the module 201 for obtaining predetermined project of inviting outside investment；
Second key message of each enterprise of the matching module 202 for obtaining project of inviting outside investment described in participation, respectively will
Second key message of each enterprise obtained is matched with first key message, to obtain each enterprise and the trade and investment promotion
The matching degree for project of bringing in funds；
If categorization module 203 is used to be greater than predefined matching degree in the matching degree for having enterprise and the project of inviting outside investment
Reference threshold, it is determined that the enterprise is the target object invited outside investment, according to predetermined target object classification method, to this
Enterprise carries out target object grade classification；
Determining module 204 is for the mapping between target object rank according to the pre-stored data and target object of inviting outside investment
Relationship, determines whether the rank of the enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the project of inviting outside investment
Recommendation.
In addition, the present invention also proposes that a kind of target object invited outside investment determines method, please refer to shown in Fig. 3, the trick
The target object that quotient brings in funds determines that method includes the following steps:
S301, the first key message in the text information of predetermined project of inviting outside investment is obtained；
Specifically, the text information of predetermined project of inviting outside investment includes the related subject invited outside investment and each master
Corresponding content information is inscribed, specifically, the text information of predetermined project of inviting outside investment can enter by given network address
Port address obtains page link, is downloaded to obtain；Further, in the present embodiment, first completed according to preparatory training
Key message marking model analyzes the text information of predetermined project of inviting outside investment, to obtain text information
In the first key message；Specifically, first key message include theme, trade classification, company information keyword such as " on
The company informations keywords such as company, city " " assets are more than 100,000,000 " " professional is no less than 50 people ", trade and investment promotion signal word are as " simultaneously
Trade and investment promotions signal word, the incentive message such as purchase ", " planning investing inside the province " etc.；
Specifically, in the present embodiment, the first key message marking model that the preparatory training is completed is neural network
Model, the pass of mark that the training process of the first key message marking model includes the following steps: E, obtains preset quantity
The text information sample of the project of inviting outside investment of key information and the corresponding urtext information of each text information sample；
F, by the corresponding urtext information of the text information sample of each project be divided into the first ratio training subset and
The test subset of second ratio；
G, it is marked using urtext information training first key message of each project in the training subset
Model, to obtain trained key message marking model；
H, mould is marked to first key message using the urtext information of each project in the test subset
Type is tested, if test passes through, training terminates, alternatively, increasing the text envelope of the training subset if test does not pass through
It ceases the quantity of sample and re-executes above-mentioned steps E, F, G.
Specifically, in the step H, the urtext information pair using each project in the test subset
The step of first key message marking model is tested include:
Utilize trained first key message mark then original of the model to each project in the test subset
Beginning text information is labeled, with obtain each project by manually carry out the third key message that marks of key message with
The equal probability value of the 4th key message that key message marks is carried out automatically by the first key message marking model；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described
Preset probability threshold value then carries out model accuracy test for the project, which is carried out artificial mark key message, with
It obtains the corresponding third key message of the project, and calls the first key message marking model automatic marking project, to obtain
Corresponding 4th key message of the project；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that tested for the model accuracy of the project
Result be correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that be directed to the project
Model accuracy test result be mistake；
It is greater than if the percentage that correct model accuracy test result accounts for all model accuracy test results default
Percentage threshold, it is determined that the test of the first key message marking model is passed through, alternatively, accurate if correct model
Property test result account for all model accuracy test results percentage be less than or equal to preset percentage threshold value, it is determined that it is right
The test of the first key message marking model does not pass through.
Second key message of each enterprise for project of inviting outside investment described in S302, acquisition participation, each enterprise that will acquire respectively
Second key message of industry is matched with first key message, to obtain each enterprise and the project of inviting outside investment
Matching degree；
Specifically, can be invited outside investment described in participation item by the second key message marking model that training is completed in advance
The text information of each enterprise of purpose carries out key message mark, to mark out corresponding second key message of each enterprise.Tool
Body, the second key message marking model is also neural network model, the training process and test process of the model
It is identical as the principle of the first key message marking model, here, being not repeated.
If S303, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold,
It determines that the enterprise is the target object invited outside investment, according to predetermined target object classification method, mesh is carried out to the enterprise
Mark object grade classification；
Specifically, predetermined target object classification method is density-based algorithms, in one embodiment, base
It is DBscan algorithm in the clustering algorithm of density, the specific density-based algorithms include: to be existed according to each target object
Data object information disclosed in preset time (for example, in the half a year nearest from current point in time), for example, enterprise's turnover, in
The data object informations such as target trade classification, the theme of bid target, trade and investment promotion signal word are marked, each target object are divided into default
The target object of rank, for example, listed company be the target object of first level, market value cross hundred million be second level target object,
Professional is no less than the target object of the pre-set levels such as the target object that 50 people are third level；Respectively with different pre-set levels
Different input objects of the target object as DBscan algorithm, it is to be understood that the target object institute of different pre-set levels
The classification of category is different, and different discrete datas, and default sweep radius e (example can be divided into according to the target object of pre-set level
Such as, e=3 indicates the minimum same data object Information Number that the target object of same pre-set level includes) and it is minimum comprising point
Minp (for example, minp=5, indicates target object of 5 class difference pre-set levels) is counted, then optional one not visited point
(target object of pre-set level) starts, and finds out within sweep radius e that (including e) point is accessed (to access the pre-set level
Target object) number, if the accessed number of the point is greater than or equal to minp within sweep radius e, the point is (current
The target object of pre-set level) and other numbers being accessed within sweep radius e formed more than or equal to minp times points
One cluster (cluster of a cluster), and starting point is marked as access point.Then recurrence handles the cluster in the same way
Interior all not visited points, to be extended to cluster.If the accessed number of the point is less than within sweep radius e
Minp, then the point be temporarily labeled as noise spot (non-cluster point, it is corresponding be in the present embodiment with the project of inviting outside investment not
The target object of relevant pre-set level), if cluster is fully extended, i.e., all the points in cluster are marked as having accessed, then use
Same algorithm goes to handle not visited point.Grade is carried out by the target object that this clustering method can invite outside investment
Do not classify.
Mapping relations between S304, target object rank according to the pre-stored data and target object of inviting outside investment determine
Whether the rank of the enterprise meets the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
By above-mentioned thing embodiment it is found that the target object proposed by the present invention invited outside investment determines method, first by obtaining
Take the first key message in the text information for obtaining predetermined project of inviting outside investment；Then the participation trade and investment promotion is obtained to draw
Second key message of each enterprise of money project, the second key message of each enterprise that will acquire respectively and the first crucial letter
Breath is matched, to obtain the matching degree of each enterprise Yu the project of inviting outside investment；If there is enterprise to draw with the trade and investment promotion again
The matching degree of money project is greater than predefined matching degree reference threshold, it is determined that the enterprise is the target object invited outside investment, root
According to predetermined target object classification method, target object grade classification is carried out to the enterprise；It is last according to the pre-stored data
Mapping relations between target object rank and target object of inviting outside investment determine whether the rank of the enterprise meets and invite outside investment
The rank of project, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.It can complete to promote trade and investment by intelligent means and draw
It provides, save a large amount of human cost, and improve the accuracy of result.
In addition, the present invention also proposes a kind of computer readable storage medium, stored on the computer readable storage medium
There is the target object invited outside investment to determine program, the target object invited outside investment determines realization when program is executed by processor
Following operation:
Obtain the first key message in the text information of predetermined project of inviting outside investment；
Obtain the second key message of each enterprise for project of inviting outside investment described in participating in, the of each enterprise that will acquire respectively
Two key messages are matched with first key message, to obtain the matching of each enterprise Yu the project of inviting outside investment
Degree；
If there is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, it is determined that should
Enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target object to the enterprise
Grade classification；
Mapping relations between target object rank according to the pre-stored data and target object of inviting outside investment, determine the enterprise
Rank whether meet the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
Computer readable storage medium specific embodiment of the present invention and above-mentioned electronic device and the target invited outside investment
Object determines that each embodiment of method is essentially identical, does not make tired state herein.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Business device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of electronic device, which is characterized in that the electronic device includes memory and the processing that connect with the memory
Device, the processor determine program for executing the target object invited outside investment stored on the memory, and the trade and investment promotion is drawn
The target object of money, which determines, realizes following steps when program is executed by the processor:
A1, the first key message in the text information of predetermined project of inviting outside investment is obtained；
A2, obtain project of inviting outside investment described in participating in each enterprise the second key message, the of each enterprise that will acquire respectively
Two key messages are matched with first key message, to obtain the matching of each enterprise Yu the project of inviting outside investment
Degree；
If A3, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, it is determined that should
Enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target object to the enterprise
Grade classification；
Mapping relations between A4, target object rank according to the pre-stored data and target object of inviting outside investment, determine the enterprise
Rank whether meet the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
2. electronic device as described in claim 1, which is characterized in that the step A1 includes:
According to the first key message marking model that preparatory training is completed, to the text information of predetermined project of inviting outside investment
It is analyzed, to obtain the first key message in text information.
3. electronic device as claimed in claim 2, which is characterized in that the first key message mark that the preparatory training is completed
Model is neural network model, and the training process of the first key message marking model includes the following steps:
E1, obtain preset quantity the project of inviting outside investment for having marked key message text information sample and each text envelope
Cease the corresponding urtext information of sample；
F1, the training subset and second that the corresponding urtext information of the text information sample of each project is divided into the first ratio
The test subset of ratio；
G1, mould is marked using urtext information training first key message of each project in the training subset
Type, to obtain trained key message marking model；
H1, using it is described test subset in each project urtext information to the first key message marking model into
Row test, if test passes through, training terminates, alternatively, increasing the text information sample of the training subset if test does not pass through
This quantity simultaneously re-executes above-mentioned steps E1, F1, G1 and H1.
4. electronic device as claimed in claim 3, which is characterized in that described to utilize test in the step H1
The step of urtext information of each project concentrated tests the first key message marking model include:
Utilize trained first key message mark then original text of the model to each project in the test subset
This information is labeled, to obtain each project by manually carrying out the third key message that marks of key message and passing through
First key message marking model carries out the equal probability value of the 4th key message that key message marks automatically；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described default
Probability threshold value, then carry out model accuracy test for the project, which be subjected to artificial mark key message, to obtain
The corresponding third key message of the project, and the first key message marking model automatic marking project is called, to obtain this
Corresponding 4th key message of mesh；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that for the knot of the model accuracy test of the project
Fruit is correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that for the mould of the project
The result of type accuracy test is mistake；
It is greater than default percentage if the percentage that correct model accuracy test result accounts for all model accuracy test results
Compare threshold value, it is determined that pass through to the test of the first key message marking model, alternatively, surveying if correct model accuracy
The percentage that test result accounts for all model accuracy test results is less than or equal to preset percentage threshold value, it is determined that described
The test of first key message marking model does not pass through.
5. electronic device as described in claim 1, which is characterized in that in the step A3, the predetermined target
Object classification method is density-based algorithms, and the density-based algorithms are DBscan algorithm.
6. a kind of target object invited outside investment determines method, which is characterized in that described method includes following steps:
S1, the first key message in the text information of predetermined project of inviting outside investment is obtained；
S2, obtain project of inviting outside investment described in participating in each enterprise the second key message, the of each enterprise that will acquire respectively
Two key messages are matched with first key message, to obtain the matching of each enterprise Yu the project of inviting outside investment
Degree；
If S3, thering is the matching degree of enterprise and the project of inviting outside investment to be greater than predefined matching degree reference threshold, it is determined that should
Enterprise is the target object invited outside investment, and according to predetermined target object classification method, carries out target object to the enterprise
Grade classification；
Mapping relations between S4, target object rank according to the pre-stored data and target object of inviting outside investment, determine the enterprise
Rank whether meet the rank for the project of inviting outside investment, if satisfied, being then automatically performed the recommendation for the project of inviting outside investment.
7. the target object invited outside investment as claimed in claim 6 determines method, which is characterized in that the step S1 includes:
According to the first key message marking model that preparatory training is completed, to the text information of predetermined project of inviting outside investment
It is analyzed, to obtain the first key message in text information.
8. the target object invited outside investment as claimed in claim 7 determines method, which is characterized in that the preparatory training is completed
The first key message marking model be neural network model, the training process of the first key message marking model includes such as
Lower step:
E2, obtain preset quantity the project of inviting outside investment for having marked key message text information sample and each text envelope
Cease the corresponding urtext information of sample；
F2, the training subset and second that the corresponding urtext information of the text information sample of each project is divided into the first ratio
The test subset of ratio；
G2, mould is marked using urtext information training first key message of each project in the training subset
Type, to obtain trained key message marking model；
H2, using it is described test subset in each project urtext information to the first key message marking model into
Row test, if test passes through, training terminates, alternatively, increasing the text information sample of the training subset if test does not pass through
This quantity simultaneously re-executes above-mentioned steps E2, F2, G2 and H2.
9. the target object invited outside investment as claimed in claim 8 determines method, which is characterized in that in the step H2,
The urtext information using each project in the test subset carries out the first key message marking model
The step of test includes:
Utilize trained first key message mark then original text of the model to each project in the test subset
This information is labeled, to obtain each project by manually carrying out the third key message that marks of key message and passing through
First key message marking model carries out the equal probability value of the 4th key message that key message marks automatically；
If the probability value for having the corresponding third key message of project equal with the 4th key message is greater than described default
Probability threshold value, then carry out model accuracy test for the project, which be subjected to artificial mark key message, to obtain
The corresponding third key message of the project, and the first key message marking model automatic marking project is called, to obtain this
Corresponding 4th key message of mesh；
Error amount between the corresponding third key message of the project being calculated and the 4th key message；
If the calculated error amount of institute is less than preset error threshold, it is determined that for the knot of the model accuracy test of the project
Fruit is correct, alternatively, if the calculated error amount of institute is greater than or equal to preset error threshold, it is determined that for the mould of the project
The result of type accuracy test is mistake；
It is greater than default percentage if the percentage that correct model accuracy test result accounts for all model accuracy test results
Compare threshold value, it is determined that pass through to the test of the first key message marking model, alternatively, surveying if correct model accuracy
The percentage that test result accounts for all model accuracy test results is less than or equal to preset percentage threshold value, it is determined that described
The test of first key message marking model does not pass through.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has the target object invited outside investment
Determine program, the target object invited outside investment determines that program can be executed by least one processor, so that described at least one
The step of target object invited outside investment that a processor executes as described in any one of claim 6-9 determines method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798138.9A CN110020191A (en) | 2018-07-19 | 2018-07-19 | Electronic device, the target object invited outside investment determine method and storage medium |
| PCT/CN2018/107726 WO2020015171A1 (en) | 2018-07-19 | 2018-09-26 | Electronic device, method and system for determining target object for investment promotion, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798138.9A CN110020191A (en) | 2018-07-19 | 2018-07-19 | Electronic device, the target object invited outside investment determine method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110020191A true CN110020191A (en) | 2019-07-16 |
Family
ID=67188361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810798138.9A Pending CN110020191A (en) | 2018-07-19 | 2018-07-19 | Electronic device, the target object invited outside investment determine method and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110020191A (en) |
| WO (1) | WO2020015171A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728540A (en) * | 2019-10-10 | 2020-01-24 | 华夏幸福产业投资有限公司 | Enterprise recommendation method, device, equipment and medium |
| CN112396550A (en) * | 2020-11-26 | 2021-02-23 | 深圳市中博科创信息技术有限公司 | Construction management method of intelligent business inviting platform |
| CN112528007A (en) * | 2019-09-19 | 2021-03-19 | 中冶赛迪重庆信息技术有限公司 | Confirmation method and confirmation device for target enterprise of business inviting project |
| CN113836373A (en) * | 2021-01-20 | 2021-12-24 | 国义招标股份有限公司 | Bidding information processing method and device based on density clustering and storage medium |
| CN116188125A (en) * | 2023-03-10 | 2023-05-30 | 深圳市伙伴行网络科技有限公司 | Business invitation management method and device for office building, electronic equipment and storage medium |
| CN117573877A (en) * | 2024-01-17 | 2024-02-20 | 安徽省优质采科技发展有限责任公司 | Supply chain collaborative management platform material data processing method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120330994A1 (en) * | 2011-06-22 | 2012-12-27 | Verisign, Inc. | Systems and Methods for Inter-Object Pattern Matching |
| CN104375998A (en) * | 2013-08-13 | 2015-02-25 | 王建平 | Intelligentized project matching analysis tool and implementation method thereof |
| CN105718580A (en) * | 2016-01-25 | 2016-06-29 | 江苏国泰新点软件有限公司 | Method and device for providing bidding information search service |
| CN106412026A (en) * | 2016-09-09 | 2017-02-15 | 上海润吧信息技术有限公司 | Public network service system based on enterprise service outsourcing |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN106960063A (en) * | 2017-04-20 | 2017-07-18 | 广州优亚信息技术有限公司 | A kind of internet information crawl and commending system for field of inviting outside investment |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN108197811A (en) * | 2018-01-04 | 2018-06-22 | 四川隧唐科技股份有限公司 | Engineering tracking and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1889078A (en) * | 2006-06-22 | 2007-01-03 | 蔡征兵 | Method for issuing information and ordering according to actual position via network searching platform |
| CN101127050A (en) * | 2007-07-03 | 2008-02-20 | 北京大学 | Method for automatically extracting website owner administrative apanage information from web page |
| CN107948596A (en) * | 2017-11-27 | 2018-04-20 | 江西文文网络科技有限公司 | A kind of villages and towns management system |
-
2018
- 2018-07-19 CN CN201810798138.9A patent/CN110020191A/en active Pending
- 2018-09-26 WO PCT/CN2018/107726 patent/WO2020015171A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120330994A1 (en) * | 2011-06-22 | 2012-12-27 | Verisign, Inc. | Systems and Methods for Inter-Object Pattern Matching |
| CN104375998A (en) * | 2013-08-13 | 2015-02-25 | 王建平 | Intelligentized project matching analysis tool and implementation method thereof |
| CN105718580A (en) * | 2016-01-25 | 2016-06-29 | 江苏国泰新点软件有限公司 | Method and device for providing bidding information search service |
| CN106412026A (en) * | 2016-09-09 | 2017-02-15 | 上海润吧信息技术有限公司 | Public network service system based on enterprise service outsourcing |
| CN106919702A (en) * | 2017-02-14 | 2017-07-04 | 北京时间股份有限公司 | Keyword method for pushing and device based on document |
| CN106960063A (en) * | 2017-04-20 | 2017-07-18 | 广州优亚信息技术有限公司 | A kind of internet information crawl and commending system for field of inviting outside investment |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
| CN108197811A (en) * | 2018-01-04 | 2018-06-22 | 四川隧唐科技股份有限公司 | Engineering tracking and device |
Non-Patent Citations (1)
| Title |
|---|
| 卢勇进: "《政府与企业招商引资战略和操作实务》", 对外经济贸易大学出版社, pages: 323 - 324 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112528007A (en) * | 2019-09-19 | 2021-03-19 | 中冶赛迪重庆信息技术有限公司 | Confirmation method and confirmation device for target enterprise of business inviting project |
| CN112528007B (en) * | 2019-09-19 | 2023-04-07 | 中冶赛迪信息技术(重庆)有限公司 | Confirmation method and confirmation device for target enterprise of business inviting project |
| CN110728540A (en) * | 2019-10-10 | 2020-01-24 | 华夏幸福产业投资有限公司 | Enterprise recommendation method, device, equipment and medium |
| CN112396550A (en) * | 2020-11-26 | 2021-02-23 | 深圳市中博科创信息技术有限公司 | Construction management method of intelligent business inviting platform |
| CN113836373A (en) * | 2021-01-20 | 2021-12-24 | 国义招标股份有限公司 | Bidding information processing method and device based on density clustering and storage medium |
| CN116028829A (en) * | 2021-01-20 | 2023-04-28 | 国义招标股份有限公司 | Correction clustering processing method, device and storage medium based on transmission step length adjustment |
| CN116028829B (en) * | 2021-01-20 | 2023-10-24 | 国义招标股份有限公司 | Correction clustering processing method, device and storage medium based on transmission step length adjustment |
| CN116188125A (en) * | 2023-03-10 | 2023-05-30 | 深圳市伙伴行网络科技有限公司 | Business invitation management method and device for office building, electronic equipment and storage medium |
| CN116188125B (en) * | 2023-03-10 | 2024-05-31 | 深圳市伙伴行网络科技有限公司 | Business invitation management method and device for office building, electronic equipment and storage medium |
| CN117573877A (en) * | 2024-01-17 | 2024-02-20 | 安徽省优质采科技发展有限责任公司 | Supply chain collaborative management platform material data processing method and system |
| CN117573877B (en) * | 2024-01-17 | 2024-03-22 | 安徽省优质采科技发展有限责任公司 | Supply chain collaborative management platform material data processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020015171A1 (en) | 2020-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020191A (en) | Electronic device, the target object invited outside investment determine method and storage medium | |
| CN109377333A (en) | Electronic device determines method and storage medium based on the collection person of disaggregated model | |
| WO2020253466A1 (en) | Method and device for generating test case of user interface | |
| US11544639B2 (en) | Data source-based service customizing device, method and system, and storage medium | |
| CN110245980B (en) | Method and equipment for determining target user excitation form based on neural network model | |
| CN109657038A (en) | The method for digging, device and electronic equipment of a kind of question and answer to data | |
| CN107967333A (en) | Voice search method, voice searching device and electronic equipment | |
| CN109918279A (en) | Electronic device, method and storage medium based on daily record data identification user's abnormal operation | |
| CN108876545A (en) | Order recognition methods, device and readable storage medium storing program for executing | |
| CN111611390B (en) | Data processing method and device | |
| CN110335139A (en) | Appraisal procedure, device, equipment and readable storage medium storing program for executing based on similarity | |
| CN110135421A (en) | Licence plate recognition method, device, computer equipment and computer readable storage medium | |
| CN109194689A (en) | Abnormal behaviour recognition methods, device, server and storage medium | |
| CN108492138A (en) | Product buys prediction technique, server and storage medium | |
| CN108763051A (en) | Electronic device, transaction software operation risk method for early warning and storage medium | |
| CN112070310A (en) | Loss user prediction method and device based on artificial intelligence and electronic equipment | |
| CN112926471A (en) | Method and device for identifying image content of business document | |
| CN109447674A (en) | Electronic device, insurance agent target service area determine method and storage medium | |
| CN109753561B (en) | Automatic reply generation method and device | |
| CN110335061A (en) | Trade mode portrait method for building up, device, medium and electronic equipment | |
| CN110059721A (en) | Floor plan area recognizing method, device, equipment and computer readable storage medium | |
| CN113472860A (en) | Service resource allocation method and server under big data and digital environment | |
| CN111784053A (en) | Transaction risk detection method, device and readable storage medium | |
| CN112801145A (en) | Safety monitoring method and device, computer equipment and storage medium | |
| CN105989103A (en) | Method for recommending application program and terminal |
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 |