CN110083634A - Order processing method, apparatus, equipment and storage medium based on data analysis - Google Patents
Order processing method, apparatus, equipment and storage medium based on data analysis Download PDFInfo
- Publication number
- CN110083634A CN110083634A CN201910207563.0A CN201910207563A CN110083634A CN 110083634 A CN110083634 A CN 110083634A CN 201910207563 A CN201910207563 A CN 201910207563A CN 110083634 A CN110083634 A CN 110083634A
- Authority
- CN
- China
- Prior art keywords
- user
- label
- target
- information
- recommended
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 39
- 238000003672 processing method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 description 10
- 238000000034 method Methods 0.000 description 8
- 230000000295 complement effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 108091068146 02 family Proteins 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of order processing methods based on data analysis, after obtaining order and assisting request, obtain potential user's information according to target order type, potential user's information includes recommended user's label；And it is identified according to target user and obtains corresponding target user's label；According to target user's label and recommended user's label, the corresponding recommender score of each potential user's information is calculated.Target recommended user and target partner user are finally determined from potential user's information according to recommender score.Guarantee to be formed precisely effective target recommended user, and the target partner user for providing complementation carries out common order and recommends, and can also be improved the efficiency of order negotiation.The invention also discloses a kind of order processing device based on data analysis and associated computer devices and storage medium.
Description
Technical field
The present invention relates to big data field more particularly to a kind of order processing method, apparatus based on data analysis, calculate
Machine equipment and storage medium.
Background technique
It usually all include back office force and field personnel at present in the enterprise for much needing to carry out business or product promotion
Personnel.And general business perhaps product promotion be all gone by field force carry out back office force generally not active business or
Product promotion.However, back office force can also have many potential customers at one's side, but most of back office force does not have wish or meaning
Know and actively recommend suitable product to potential customers, causes the loss of a part of potential customers.Also, even if existing sporadicly
Lead referral behavior also all only simply or randomly gives the lead referral to a business personnel, and cannot be formed precisely has
The lead referral of effect also influences the negotiation of follow-up business.
Summary of the invention
The embodiment of the present invention provides a kind of order processing method, apparatus, computer equipment and storage based on data analysis
Medium, to solve the problems, such as that order recommends validity not high.
A kind of order processing method based on data analysis, comprising:
It obtains order and assists request, it includes target user's mark and target order type that the order, which assists request,；
Potential user's information is obtained according to the target order type, potential user's information includes recommended user's mark
Label；
It is identified according to the target user and obtains corresponding target user's label；
According to target user's label and recommended user's label, it is corresponding to calculate each potential user's information
Recommender score；
Target recommended user and target partner user are determined from potential user's information according to the recommender score.
A kind of order processing device based on data analysis, comprising:
Order assists request module, assists request for obtaining order, it includes that target is used that the order, which assists request,
Family mark and target order type；
Potential user's data obtaining module, it is described latent for obtaining potential user's information according to the target order type
It include recommended user's label in user information；
Target user's label acquisition module obtains corresponding target user's label for identifying according to the target user；
Recommender score computing module, for calculating each according to target user's label and recommended user's label
The corresponding recommender score of potential user's information；
Information determination module, for determining target recommended user from potential user's information according to the recommender score
With target partner user.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize the above-mentioned order based on data analysis when executing the computer program
The step of processing method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the step of above-mentioned order processing method based on data analysis when being executed by processor.
In the above-mentioned order processing method, apparatus based on data analysis, computer equipment and storage medium, order is being obtained
After assisting request, potential user's information is obtained according to target order type, potential user's information includes recommended user's label；And
It is identified according to target user and obtains corresponding target user's label；According to target user's label and recommended user's label, meter
Calculate the corresponding recommender score of each potential user's information.Finally determine that target is recommended from potential user's information according to recommender score
User and target partner user.Guarantee to be formed precisely effective target recommended user, and complementary target partner user is provided
It carries out common order to recommend, can also be improved the efficiency of order negotiation.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 2 is an exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 3 is another exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 4 is another exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 5 is another exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 6 is another exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 7 is another exemplary diagram of the order processing method based on data analysis in one embodiment of the invention；
Fig. 8 is a functional block diagram of the order processing device based on data analysis in one embodiment of the invention；
Fig. 9 is another functional block diagram of the order processing device based on data analysis in one embodiment of the invention
Figure 10 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Order processing method provided in an embodiment of the present invention based on data analysis, can be applicable to the application environment such as Fig. 1
In, wherein computer equipment (client) is communicated by network with server-side.Client sends order and assists request to clothes
Business end, server-side obtain potential user's information after obtaining order and assisting request, according to target order type, and potential user believes
Breath includes recommended user's label；And it is identified according to target user and obtains corresponding target user's label；According to target user's label
With recommended user's label, the corresponding recommender score of each potential user's information is calculated.Finally according to recommender score from potential user
Target recommended user and target partner user are determined in information.Wherein, computer equipment (client) can be, but not limited to various
Personal computer, laptop, smart phone, tablet computer and portable wearable device.Server-side can be with independent
The server cluster of server either multiple servers composition is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of order processing method based on data analysis, answers in this way
It is illustrated, includes the following steps: for the server-side in Fig. 1
S10: it obtains order and assists request, it includes target user's mark and target order type that order, which assists request,.
Wherein, it is the assistance request initiated from client to server-side that order, which assists request, and order assistance can serve as reasons
Specified order type and request customer resources or the technical assistance of request.Target user is identified as initiation and orders
Single corresponding mark of user for assisting request, target user mark can be ID card No., phone number or user's account
Number etc..It optionally, can also include the process of a login authentication before obtaining order and assisting request, i.e. user passes through visitor
The login interface at family end carries out the input and verifying of account information, to be verified to assist request by generating the order later, can be with
Target user's mark is obtained according to the user account in account information, or is directly marked user account as target user
Know.Order assists to further comprise target order type in request, and target order type is assisted for distinguishing different orders in order
Helping target order type in request to be used to identify, assisted is which kind order.Illustratively, it goes in insurance
In industry, target order type can be accident insurance, serious illness insurance or endowment insurance etc..The target order type can be by different
Text distinguishes, and can also be indicated by number, character or symbol etc..
In one embodiment, target user's mark is an enterprise for identifying different field forces, field force
In industry and client carries out the harmonious light personnel of promoting service.And opposite with field force is back office force, back office force is negative
Blame the general designation of the personnel of enterprises affairs.And in this embodiment, order is initiated by client by field force
Assist request.
S20: potential user's information is obtained according to target order type, potential user's information includes recommended user's label.
Wherein, potential user's information refers to that collects in advance can be determined as the related letter of the potential user of the order type
Breath.Recommended user's label refers to label corresponding to the user (back office force) for recommending the potential user, recommended user's label
The professional ability of the user can be embodied, be good at the information such as field or the qualification time limit.For example, a certain product is especially understood,
It is either familiar to some service link or have relevant speciality etc., recommended user's label can be formed.Specifically, should
Recommended user's label can be embodied by least one of text, number, letter or symbol etc..In one embodiment,
Recommended user's label can recommend label corresponding to the back office force of the potential user for expression.
It is alternatively possible to pre-establish recommended user's information bank, there may be business for back office force's collection of Xiang Qiye
The information of the user of demand, i.e. recommended user's information form recommended user's information bank after summarizing recommended user's information.Its
In, each recommended user's information further includes the label of corresponding back office force other than including the relevant information of recommended user,
That is recommended user's label, recommended user's label are used to reflect the professional ability of the back office force, are good at field or qualification year
Limit etc..Preferably, each recommended user's information in recommended user's information bank can also include recommending order type, that is, mark
The recommended user may it is interested or need order type.Preferably, which can be by recommendation
User information can be only generated after being analyzed.Such as: different keywords is set for different order types in advance, the keyword
It can be the information such as age, occupation, gender or physical condition.Then according to the keyword of different order types in recommended user
It is matched in information, the order type of successful match is determined as to the recommendation order type of the recommended user, and then to recommend
User information, which generates, recommends order type.
In this step, it is inquired in recommended user's information bank according to target order type, is used if inquiring recommendation
In the information of family exist and the matched recommendation order type of target order type, then obtain recommended user's information as potential user
Information, or obtain to do after recommended user's information and further screen, obtain potential user's information.
S30: it is identified according to target user and obtains corresponding target user's label.
In this step, target user's label is the corresponding user tag of user initiated order and assist request, the target
User tag is similar with recommended user's label, is also used for embodying the professional ability of the user, is good at field or the qualification time limit etc..
It can be that each user generates target user's label, and the target user by carrying out the link of user tag data collection in advance
Label is associated with target user's mark, therefore can be inquired by target user's mark in this step and be got corresponding mesh
Mark user tag.
S40: according to target user's label and recommended user's label, the corresponding recommended hour of each potential user's information is calculated
Number.
In this step, it by matching target user's label and recommended user's label, and then obtains each potential
The corresponding recommender score of user information.Wherein, the corresponding user of target user's label is usually field force, and recommended user marks
Signing corresponding user is usually back office force, and the field or business aspect that the two is good at are different more.Therefore, pass through target
User tag and recommended user's label, have complementary advantages, and can preferably provide for the negotiation or recommendation of subsequent business
Perfect support facilitates the recommendation and signing of preferably finishing service.For example, program or stream of the field force to business
Journey is familiar with, and back office force may be familiar with specific business rule or clause, the two combination carry out business
Recommend or consulting is more conducive to carry out the development of related service.
Specifically, the formulation of tag match rule can be carried out in advance, it is possible to specify which label is complementary label, or
A benchmark score value is set for each label, sets in a business score value can be higher there are which label, it can be with root
Different tag match rules is set according to specific different business.Illustratively, if the label of the corresponding needs of a business is
01,02 and 03, then it is most suitable take that the tag match rule of the business, which can be set as 01,02 and 03 3 label of needs,
Match, and can be respectively that three labels set different weights, such as in this example, label 02 is mostly important, and label
03 takes second place.Illustratively, the score value sequentially distributed for 01,02 and 03 3 label is respectively 2,5 and 3.
After setting tag match rule, according to target user's label and recommended user's label combination tag matching rule
It is then calculated, obtains the corresponding recommender score of each potential user's information.For example, recommending to use if target user's label is 02
Family label is 03, then is 8 according to the score that tag match rule is calculated.
Further, different grades can also be distributed for each label, for example, generally, be familiar with, be proficient in.And it is
Different ranking scores matches different score values, to guarantee available more accurate recommender score.I.e. in the difference of each label
Grade has all further refined different score values.For example, the score value of a label is 2, then it can further be different grades
Finer score value is refined, higher grade, and corresponding score value is then higher.Highest level can be corresponded to full marks value (2).Example
Property, distribute different grades if each label, for example, generally, be familiar with and be proficient in, then can will be every in these three grades
The corresponding score value of one grade carries out trisection.For example, general corresponding score value is the one third of the label score value, it is familiar with corresponding to
Score value be the label score value 2/3rds, be proficient in corresponding score value be the label score value whole score values.Optionally, if
All include the same label in target user's label and recommended user's label, then grade can be taken higher as scoring according to
According to.Guarantee that recommender score obtains more accurate by this mode.
S50: target recommended user and target partner user are determined from potential user's information according to recommender score.
After obtaining recommender score, target recommended user is determined from potential user's information according to recommender score.Specifically
Ground, can preset it needs to be determined that target recommended user quantity, then take recommender score highest right according to the quantity
Potential user's information of quantity is answered, and determines that the corresponding user of potential user's information is target recommended user.Alternatively, one point of setting
Number threshold value, is all determined as target for the corresponding user of potential user's information that recommender score is more than or equal to the score threshold and pushes away
Recommend user.It is configured it is further possible to comprehensively consider above-mentioned two situations, for example, first judgement is more than score threshold
The quantity of potential user's information carries out further if this quantity is greater than the quantity of preset target recommended user
Screening, obtains the target recommended user of predetermined quantity.If this quantity is less than the quantity of preset target user, directly
Target recommended user is determined from the potential user's information of this part.
And target partner user is to recommend the back office force of target recommended user, can determine target recommended user
Later, corresponding target partner user is got according to target recommended user.
In the present embodiment, after obtaining order and assisting request, potential user's information is obtained according to target order type,
Potential user's information includes recommended user's label；And it is identified according to target user and obtains corresponding target user's label；According to mesh
User tag and recommended user's label are marked, the corresponding recommender score of each potential user's information is calculated.Finally according to recommendation
Score determines target recommended user and target partner user from potential user's information.Guarantee to be formed precisely effective target to recommend
User, and complementary target partner user is provided and carries out common order recommendation, it can also be improved the efficiency of order negotiation.
In one embodiment, it as shown in figure 3, according to target user's label and recommended user's label, calculates each potential
The corresponding recommender score of user information, specifically includes:
S41: obtaining label information table, carries out vector to target user's label and recommended user's label according to label information table
Conversion, obtains feature vector.
Wherein, label information table is the information table of label required for embodiment business.For example, completing needed for a business
Label is 01,02,03 and 04.After obtaining label information table, to target user's label and recommend to use according to label information table
Family label carries out vector conversion.Specifically, a feature vector is arranged according to label information table, then by target user's label and pushed away
It recommends user tag and label information table is matched, if successful match, the element value of corresponding position is 1 in feature vector, if
It fails to match, then the element value of corresponding position is 0 in feature vector.Illustratively, a feature vector A=[a is set1, a2...,
an], wherein n is the quantity of label in label information table.Again by by target user's label and recommended user's label and label
Information table is matched.For example, recommended user's label is 03 if target user's label is 01 and 02, then feature vector is A=
[1,1,1,0].
Optionally, if there are duplicate label in target user's label and recommended user's label, can also will feature to
It is embodied in amount, for example, the element value of corresponding position is designated as 1.5 or 2.Specific value can carry out according to actual needs
Setting.
S42: according to preset weight coefficient and feature vector, the corresponding recommender score of each potential user's information is calculated.
Wherein, weight coefficient is the further embodiment to the significance level of element value (label) each in feature vector.
It can guarantee that the acquisition of recommender score is more accurate by the setting of weight coefficient.Specifically, by every unitary in feature vector
Plain value arrives the corresponding recommender score of each potential user's information multiplied by summing after corresponding weight coefficient.
In this embodiment, it after obtaining label information table, to target user's label and is pushed away according to label information table
It recommends user tag and carries out feature vector conversion, obtain feature vector；And it according to preset weight coefficient and feature vector, calculates
The corresponding recommender score of each potential user's information ensure that the accuracy that recommender score calculates.
In one embodiment, potential user's information includes recommended user's scoring.
Wherein, recommended user's scoring is the internal feedback score of a user, and user scoring can reflect the user's
Cooperation situation, business real standard or business handling efficiency etc..Optionally, user scoring can be cooperated by other
User gives a mark to it to obtain, or is realized by one code of points of setting.It is to be appreciated that user scoring is got over
Height then illustrates that the professional skill of corresponding user or priority are higher.
In this embodiment, it as shown in figure 4, according to target user's label and recommended user's label, calculates each potential
The corresponding recommender score of user information, specifically includes:
S41 ': obtain label information table, according to label information table to target user's label and recommended user's label carry out to
Amount conversion, obtains feature vector.
S42 ': according to preset weight coefficient and feature vector, the corresponding target fractional of each potential user's information is calculated.
Specifically, the step S41 and S42 in step S41 ' and S42 ' and above-described embodiment are almost the same, no longer superfluous herein
It states.
S43 ': according to user's scoring and target fractional, recommender score is obtained.
It is obtaining target fractional and then is being scored by user, increasing a Consideration and recommender score is determined.
Specifically, directly user can be scored and is added with target fractional, obtain recommender score.Or it is set according to preparatory for the two
It sets ground weight to be added to be weighted, obtains recommender score.
In the present embodiment, recommender score is obtained by introducing user's scoring, further ensures that recommender score calculates
Accuracy.
In one embodiment, as shown in figure 5, label information table is obtained, according to label information table to target user's label
Feature vector conversion is carried out with recommended user's label, feature vector is obtained, specifically includes:
S411: label information table is obtained according to target order type, label information table includes benchmark label.
In this step, different label information tables is set for different order types in advance, in each label information table
Including benchmark label, it is possible to understand that ground, the quantity of benchmark label are at least one.The industry as required for different types of order
Business ability often will be different, and therefore, different label information tables, label information is pre-configured with according to different order types
Professional ability needed for benchmark label in table then characterizes the order type.It, can be with after pre-configured label information table
The label information table of different order types is stored in server-side.Therefore, in this step, pass through target order type
Get corresponding label information table.
S412: feature vector is established according to the quantity of benchmark label, feature vector includes characteristic element, each characteristic element
It is corresponding with a benchmark label.
In this step, feature vector is first established according to the quantity of benchmark label, specifically, according to the quantity of benchmark label
Same amount of characteristic element is set for this feature vector.For example, establishing feature vector A=[a1, a2..., an], on the basis of n
The quantity of label, and each characteristic element and a benchmark label are corresponding in this feature vector.
S413: each benchmark label and target user's label and recommended user's label are matched, and are tied according to matching
Fruit sets the element value of corresponding characteristic element in feature vector.
Each benchmark label is matched with target user's label and recommended user's label respectively, as long as being used in target
Exist in family label or recommended user's label and the label of the benchmark label successful match, then matching result is successful match；
If being all not present in target user's label and recommended user's label and the label of the benchmark label successful match, matching result
For it fails to match.The element value of corresponding characteristic element in feature vector is set according to matching result.Illustratively, matching is tied
Fruit is that the element value of the corresponding characteristic element of benchmark label of successful match is set as 1, is the benchmark that it fails to match by matching result
The element value of the corresponding characteristic element of label is set as 0.
Further, it if further comprising corresponding levels characteristic in target user's label and recommended user's label, that is, measures
Grasping level of the user to the corresponding business of the label.Such as: it is general, skilled and be proficient in.Then by each benchmark label and
Target user's label and recommended user's label match and then the matching result of successful match in further according to
The levels characteristic of corresponding label sets the element value of corresponding characteristic element in feature vector.For example, respectively will be general, skilled
Be proficient in that be correspondingly arranged be 1,2 and 3.
In the present embodiment, label information table is first obtained according to target order type, label information table includes benchmark label；
Feature vector is established further according to the quantity of benchmark label, feature vector includes characteristic element, each characteristic element and a benchmark
Label is corresponding；Finally each benchmark label and target user's label and recommended user's label are matched, tied according to matching
Fruit sets the element value of corresponding characteristic element in feature vector, ensure that the accuracy and efficiency of feature vector setting.
In one embodiment, it as shown in fig. 6, obtaining potential user's information according to order type, specifically includes:
S21: matching inquiry is carried out in recommended user's information bank according to target order type, obtains the target of successful match
User information, each target user's information include recommended user's scoring.
It in this step, is index, the matching inquiry in recommended user's information bank, by match information with target order type
It is come out in library with target user's acquisition of information of target order type successful match, wherein each target user's information includes pushing away
Recommend user's scoring.Recommended user's scoring is the internal feedback score of a user, which, which scores, can reflect the industry of the user
Business cooperation, business real standard or business handling efficiency etc..Optionally, user scoring can be used by other cooperations
Family gives a mark to it to obtain, or is realized by one code of points of setting.It is to be appreciated that user scoring is higher, then
Illustrate that professional skill or the priority of corresponding user are higher.
S22: target user's information is ranked up according to recommended user's scoring, obtains target user's sequence.
According to recommended user scoring target user's information is ranked up, it is alternatively possible to according to recommended user scoring from
Small sequence is arrived greatly to be ranked up target user's information, or target is used according to the sequence of recommended user's scoring from small to large
Family information is ranked up, and obtains target user's sequence.
S23: the user information of preset quantity is obtained from target user's sequence, is determined as potential user's information.
Wherein, preset quantity is a preset value, which can be set according to actual needs, for example, 5,
10,20 or 50 etc..In target user's sequence, obtains, obtain since recommended user scores maximum value according to preset quantity
The user information of preset quantity is determined as potential user's information.If according to the sequence of recommended user's scoring from big to small to target
User information is ranked up, then directly sequentially takes the user information of preset quantity to be determined as potential user from target user's sequence
Information.If being ranked up according to the sequence of recommended user's scoring from small to large to target user's information, from target user's sequence
In up take the user information of preset quantity to be determined as potential user's information from bottom.
In the present embodiment, matching inquiry, acquisition are first carried out in recommended user's information bank according to target order type
With successful target user's information, each target user's information includes recommended user's scoring；It is scored according to recommended user to target
User information is ranked up, and obtains target user's sequence；The user information of preset quantity is finally obtained from target user's sequence,
It is determined as potential user's information, ensure that the efficiency of potential user's acquisition of information.
In one embodiment, as shown in fig. 7, being obtained carrying out matching inquiry in customer data base according to order type
Before taking target user's information of successful match, it is somebody's turn to do the order processing method that analyzed based on data further include:
S211: using internal or office work user identifier as searching keyword, the corresponding cooperation score data of internal or office work user identifier is obtained.
Wherein, internal or office work user identifier is to distinguish the unique identification of different back office forces, which can be
ID card No., phone number or user account etc..Cooperating score data is each field personnel user in history cooperative business
To the score information of internal or office work user.The cooperation score data is index with internal or office work user identifier.Therefore, pass through internal or office work user
It is identified as searching keyword, the cooperation score data of the corresponding user of the internal or office work user identifier can be inquired.
S212: counting the cooperation score data of same internal or office work user identifier within a preset time, obtains recommended user's scoring.
Preset time is a preset time value, optionally, the preset time can for 1 month, 3 months or
Half a year.After obtaining the corresponding cooperation score data of internal or office work user identifier, according to preset time come to cooperation score data into
Row screening, screening meet the cooperation score data of preset time, then to this part meet the cooperation score data of preset time into
Row statistics obtains recommended user's scoring.It is alternatively possible to average after cooperation score data is counted, to obtain
Recommended user's scoring.
In the present embodiment, first using internal or office work user identifier as searching keyword, the corresponding cooperation of internal or office work user identifier is obtained
Score data；The cooperation score data of same internal or office work user identifier within a preset time is counted again, is obtained recommended user's scoring, is protected
The accuracy that recommended user's score data determines is demonstrate,proved.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of order processing device based on data analysis, the order that should be analyzed based on data are provided
Order processing method based on data analysis in processing unit and above-described embodiment corresponds.As shown in figure 8, data should be based on
The order processing device of analysis includes that order assists request module 10, potential user's data obtaining module 20, target user
Label acquisition module 30, recommender score computing module 40 and information determination module 50.Detailed description are as follows for each functional module:
Order assists request module 10, assists request for obtaining order, it includes target user that order, which assists request,
Mark and target order type；
Potential user's data obtaining module 20, it is described potential for obtaining potential user's information according to target order type
User information includes recommended user's label；
Target user's label acquisition module 30 obtains corresponding target user's label for identifying according to target user；
Recommender score computing module 40, for calculating each described latent according to target user's label and recommended user's label
In the corresponding recommender score of user information；
Information determination module 50, for determining target recommended user and target from potential user's information according to recommender score
Partner user.
Preferably, as shown in figure 9, recommender score computing module 40 includes feature vector conversion unit 41 and recommender score meter
Calculate unit 42.
Feature vector conversion unit 41, for obtaining label information table, according to label information table to target user's label and
Recommended user's label carries out vector conversion, obtains feature vector；
Recommender score computing unit 42, for calculating each potential user according to preset weight coefficient and feature vector
The corresponding recommender score of information.
Preferably, recommender score computing module 40 is also used to obtain label information table, is used according to label information table target
Family label and recommended user's label carry out vector conversion, obtain feature vector；According to preset weight coefficient and feature vector, meter
Calculate the corresponding target fractional of each potential user's information；According to user's scoring and target fractional, recommender score is obtained.
Preferably, feature vector conversion unit 41 includes that label information table obtains subelement, feature vector establishes subelement
With tag match subelement.
Label information table obtains subelement, for obtaining label information table, the label information according to target order type
Table includes benchmark label；
Feature vector establishes subelement, and for establishing feature vector according to the quantity of benchmark label, feature vector includes spy
Element is levied, each characteristic element and a benchmark label are corresponding；
Tag match subelement is used for each benchmark label and the progress of target user's label and recommended user's label
Match, the element value of corresponding characteristic element in feature vector is set according to matching result.
Preferably, potential user's data obtaining module 20 is also used to according to target order type in recommended user's information bank
Matching inquiry is carried out, target user's information of successful match is obtained, each target user's information includes recommended user's scoring；According to
Recommended user's scoring is ranked up target user's information, obtains target user's sequence；It is obtained from target user's sequence default
The user information of quantity is determined as potential user's information.
Preferably, it should be also used to based on the order processing device that data are analyzed using internal or office work user identifier as searching keyword,
Obtain the corresponding cooperation score data of internal or office work user identifier；Count the cooperation scoring of same internal or office work user identifier within a preset time
Data obtain recommended user's scoring.
Specific restriction about the order processing device analyzed based on data may refer to above for based on data point
The restriction of the order processing method of analysis, details are not described herein.Each mould in the above-mentioned order processing device based on data analysis
Block can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independence
In processor in computer equipment, it can also be stored in a software form in the memory in computer equipment, in order to
Processor, which calls, executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 10.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the data that the order processing method based on data analysis in above-described embodiment uses.
The network interface of the computer equipment is used to communicate with external terminal by network connection.The computer program is held by processor
To realize a kind of order processing method based on data analysis when row.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor execute computer program when realize in above-described embodiment based on number
According to the order processing method of analysis.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the order processing method based on data analysis in above-described embodiment when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of order processing method based on data analysis characterized by comprising
It obtains order and assists request, it includes target user's mark and target order type that the order, which assists request,；
Potential user's information is obtained according to the target order type, potential user's information includes recommended user's label；
It is identified according to the target user and obtains corresponding target user's label；
According to target user's label and recommended user's label, the corresponding recommendation of each potential user's information is calculated
Score；
Target recommended user and target partner user are determined from potential user's information according to the recommender score.
2. the order processing method as described in claim 1 based on data analysis, which is characterized in that described according to the target
User tag and recommended user's label calculate the corresponding recommender score of each potential user's information, comprising:
Label information table is obtained, target user's label and recommended user's label are carried out according to the label information table
Vector conversion, obtains feature vector；
According to preset weight coefficient and described eigenvector, the corresponding recommender score of each potential user's information is calculated.
3. the order processing method as described in claim 1 based on data analysis, which is characterized in that described according to the target
User tag and recommended user's label calculate the corresponding recommender score of each potential user's information, comprising:
Label information table is obtained, target user's label and recommended user's label are carried out according to the label information table
Vector conversion, obtains feature vector；
According to preset weight coefficient and described eigenvector, the corresponding target fractional of each potential user's information is calculated；
According to user scoring and target fractional, recommender score is obtained.
4. the order processing method as claimed in claim 2 or claim 3 based on data analysis, the acquisition label information table, according to
The label information table carries out vector conversion to target user's label and recommended user's label, obtains feature vector,
Include:
Label information table is obtained according to the target order type, the label information table includes benchmark label；
Feature vector is established according to the quantity of benchmark label, described eigenvector includes characteristic element, each characteristic element
It is corresponding with a benchmark label；
Each benchmark label and target user's label and recommended user's label are matched, according to matching result
Set the element value of corresponding characteristic element in feature vector.
5. the order processing method as described in claim 1 based on data analysis, which is characterized in that described according to the target
Order type obtains potential user's information, comprising:
Matching inquiry is carried out in recommended user's information bank according to target order type, obtains target user's letter of successful match
Breath, each target user's information include recommended user's scoring；
Target user's information is ranked up according to recommended user scoring, obtains target user's sequence；
The user information that preset quantity is obtained from target user's sequence, is determined as potential user's information.
6. the order processing method as claimed in claim 5 based on data analysis, which is characterized in that ordered described according to target
Single type carries out matching inquiry in recommended user's information bank, described to be based on before the target user's information for obtaining successful match
The order processing method of data analysis further include:
Using internal or office work user identifier as searching keyword, the corresponding cooperation score data of internal or office work user identifier is obtained；
The cooperation score data of the same internal or office work user identifier within a preset time is counted, recommended user's scoring is obtained.
7. a kind of order processing device based on data analysis characterized by comprising
Order assists request module, assists request for obtaining order, it includes that target user marks that the order, which assists request,
Know and target order type；
Potential user's data obtaining module, for obtaining potential user's information, the potential use according to the target order type
Family information includes recommended user's label；
Target user's label acquisition module obtains corresponding target user's label for identifying according to the target user；
Recommender score computing module, for calculating each described according to target user's label and recommended user's label
The corresponding recommender score of potential user's information；
Information determination module, for determining target recommended user and mesh from potential user's information according to the recommender score
Mark partner user.
8. the order processing device as claimed in claim 7 based on data analysis, which is characterized in that the recommender score calculates
Module includes:
Feature vector conversion unit, for obtaining label information table, according to the label information table to target user's label
Vector conversion is carried out with recommended user's label, obtains feature vector；
Recommender score computing unit, for calculating each potential user's letter according to preset weight coefficient and described eigenvector
Cease corresponding recommender score.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
Described in 6 any one based on data analysis order processing method the step of.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In order of the realization based on data analysis as described in any one of claim 1 to 6 when the computer program is executed by processor
The step of processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910207563.0A CN110083634B (en) | 2019-03-19 | 2019-03-19 | Order processing method, device, equipment and storage medium based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910207563.0A CN110083634B (en) | 2019-03-19 | 2019-03-19 | Order processing method, device, equipment and storage medium based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083634A true CN110083634A (en) | 2019-08-02 |
| CN110083634B CN110083634B (en) | 2024-02-06 |
Family
ID=67412566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910207563.0A Active CN110083634B (en) | 2019-03-19 | 2019-03-19 | Order processing method, device, equipment and storage medium based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083634B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125544A (en) * | 2019-12-20 | 2020-05-08 | 腾讯数码（天津）有限公司 | User recommendation method and device |
| CN111681743A (en) * | 2020-05-09 | 2020-09-18 | 北京启云数联科技有限公司 | Service object recommendation method, system and device |
| CN113674065A (en) * | 2021-08-30 | 2021-11-19 | 中国平安人寿保险股份有限公司 | Service contact-based service recommendation method and device, electronic equipment and medium |
| CN113763066A (en) * | 2020-06-18 | 2021-12-07 | 北京京东振世信息技术有限公司 | Method and apparatus for analyzing information |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105824963A (en) * | 2016-03-31 | 2016-08-03 | 北京小度信息科技有限公司 | Order recommendation method and device |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN109034935A (en) * | 2018-06-06 | 2018-12-18 | 平安科技（深圳）有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| CN109146292A (en) * | 2018-08-27 | 2019-01-04 | 广州飞磨科技有限公司 | Game training mate order allocation method, device, computer equipment and storage medium |
| CN109190925A (en) * | 2018-08-13 | 2019-01-11 | 中国平安人寿保险股份有限公司 | Declaration form recommended method, device, computer equipment and storage medium |
-
2019
- 2019-03-19 CN CN201910207563.0A patent/CN110083634B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105824963A (en) * | 2016-03-31 | 2016-08-03 | 北京小度信息科技有限公司 | Order recommendation method and device |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107424043A (en) * | 2017-06-15 | 2017-12-01 | 北京三快在线科技有限公司 | A kind of Products Show method and device, electronic equipment |
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN109034935A (en) * | 2018-06-06 | 2018-12-18 | 平安科技（深圳）有限公司 | Products Show method, apparatus, computer equipment and storage medium |
| CN109062994A (en) * | 2018-07-04 | 2018-12-21 | 平安科技（深圳）有限公司 | Recommended method, device, computer equipment and storage medium |
| CN109190925A (en) * | 2018-08-13 | 2019-01-11 | 中国平安人寿保险股份有限公司 | Declaration form recommended method, device, computer equipment and storage medium |
| CN109146292A (en) * | 2018-08-27 | 2019-01-04 | 广州飞磨科技有限公司 | Game training mate order allocation method, device, computer equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111125544A (en) * | 2019-12-20 | 2020-05-08 | 腾讯数码（天津）有限公司 | User recommendation method and device |
| CN111681743A (en) * | 2020-05-09 | 2020-09-18 | 北京启云数联科技有限公司 | Service object recommendation method, system and device |
| CN113763066A (en) * | 2020-06-18 | 2021-12-07 | 北京京东振世信息技术有限公司 | Method and apparatus for analyzing information |
| CN113763066B (en) * | 2020-06-18 | 2023-11-03 | 北京京东振世信息技术有限公司 | Method and device for analyzing information |
| CN113674065A (en) * | 2021-08-30 | 2021-11-19 | 中国平安人寿保险股份有限公司 | Service contact-based service recommendation method and device, electronic equipment and medium |
| CN113674065B (en) * | 2021-08-30 | 2023-09-22 | 中国平安人寿保险股份有限公司 | Service contact-based service recommendation method and device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083634B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110083634A (en) | Order processing method, apparatus, equipment and storage medium based on data analysis | |
| US8150714B2 (en) | System and method for providing healthcare-related services | |
| WO2017074494A1 (en) | Method and system for performing a probabilistic topic analysis of search queries for a customer support system | |
| US20110093457A1 (en) | Method for calculating resource points of resource information and distributing points | |
| US9600788B2 (en) | Crowdsourcing directory system | |
| CN111626784A (en) | Enterprise demand information matching method, device and system | |
| US20190066154A1 (en) | Escrow Agent for Conversion Verification | |
| CN111858686B (en) | Data display method, device, terminal equipment and storage medium | |
| US11386263B2 (en) | Automatic generation of form application | |
| CN110019774B (en) | Label distribution method, device, storage medium and electronic device | |
| CN114037504A (en) | Collection, recruitment and bidding system based on Internet | |
| US20020147596A1 (en) | On-line laboratory services brokerage system | |
| US20180225767A1 (en) | Investment management proposal system | |
| EP3382618A1 (en) | Method of evaluation processing, information processing apparatus and program | |
| US20190066150A1 (en) | Escrow Agent for Conversion Verification | |
| KR20200130767A (en) | Method and device for evaluating whether cryptocurrency is listed on cryptocurrency market using artificial neural network | |
| CN110298686B (en) | Product return fee allocation method and device, computer equipment and storage medium | |
| CN107741932A (en) | User data fusion method and system | |
| CN113241134A (en) | Online consulting doctor distribution method and system and storage medium | |
| CN111461824A (en) | Interface display method, electronic device and computer readable storage medium | |
| CN111506826A (en) | User recommendation method, device, equipment and storage medium based on intimacy | |
| KR20160074139A (en) | A sales process of variable insurance | |
| JP7244934B2 (en) | Loan decision system, loan decision method, and loan decision program | |
| US11861384B2 (en) | Methods and systems for generating recommendations based on explainable decision trees for users of a software application | |
| JP2019135631A (en) | Financial statement interpretation support device, and computer program |
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 |