CN111367942A

CN111367942A - Address book retrieval method and device

Info

Publication number: CN111367942A
Application number: CN202010236187.0A
Authority: CN
Inventors: 朱义毅; 屠方轫; 王超
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2020-03-30
Filing date: 2020-03-30
Publication date: 2020-07-03
Anticipated expiration: 2040-03-30
Also published as: CN111367942B

Abstract

According to the address book retrieval method and device, the multi-dimensional attribute characteristics of each participle are obtained by splitting the entry to be searched, then the obtained multi-dimensional attribute characteristics are input into the decision tree model, the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, model tuning is continuously performed by combining the machine learning function of the decision tree model, so that manual rule intervention is reduced, basic services of universality and convenience are provided, and the use experience of the system is improved.

Description

Address book retrieval method and device

Technical Field

The invention relates to the technical field of address book retrieval, in particular to an address book retrieval method and device.

Background

The internal address book of the enterprise is mainly used for communication among the employees in the working process, in most cases, the contact range of the employees is relatively stable within a certain time, and the contact range of the employees can be greatly changed along with the change of the posts. Especially, when a group enterprise has hundreds of thousands of employees, the conditions of employee post adjustment, communication, borrowing and the like often occur, and the conditions of duplicate names, rare words and multinational nationality of the names of the employees are relatively prominent. Therefore, it is difficult to reflect the communication relationship after the work change in time through a single personal relationship map. Furthermore, the level of protection of employee privacy information (mobile phone, home phone, emergency contact information, etc.) is relatively complex. How to improve the accuracy of the address book of the enterprise and improve the use experience of the address book so as to smoothly develop work is an urgent problem to be solved.

Disclosure of Invention

The invention provides an address book retrieval method and device aiming at the problems in the prior art.

In order to solve the technical problems, the invention provides the following technical scheme:

in one aspect of the present invention, a method for searching an address book is provided, where the address book includes a plurality of content classifications, and the method includes:

splitting a word to be searched strip input by a user to obtain a plurality of participles; each of the segments belongs to one of the content classifications, and each of the segments contains a multi-dimensional attribute feature; each dimension attribute feature comprises a plurality of different feature contents;

inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation between the feature content and the content classification and the probability under each attribute characteristic;

determining the content classification of each participle based on each corresponding relation, and generating a retrieval combination;

and searching in the address book based on the searching combination.

In a preferred embodiment, the content classification includes: name, organization name, post name, telephone number.

In a preferred embodiment, the attribute features include:

the character length, the word type and the sequence of the entry to be searched in which the participle is positioned.

In a preferred embodiment, further comprising:

establishing a plurality of initial decision tree models;

and training each initial decision tree model by using the query entries with the labeled word segmentation content classification to obtain a plurality of decision tree models.

In a preferred embodiment, the determining the content classification to which each word segmentation belongs based on each corresponding relationship includes:

generating the average probability of all the characteristic contents under each content classification according to each corresponding relation;

and selecting the content classification with the maximum corresponding average probability to determine the content classification corresponding to the word segmentation.

In a preferred embodiment, the retrieving in the address book based on the retrieval combination includes:

retrieving a plurality of personnel information which accord with the content classification limited by the retrieval combination according to the retrieval combination;

determining a first sequence number of each personnel information in a personal relationship map corresponding to the user and a second sequence number in a group relationship map according to the user identity of the input entry to be checked;

generating an arrangement serial number of each piece of personnel information relative to the user according to the first serial number, the second serial number, the personal relationship map weight and the group relationship map weight corresponding to the user;

and sequentially displaying the information of the persons to be displayed according to the generated serial number.

In a preferred embodiment, the retrieving in the address book based on the retrieval combination further includes:

determining the viewing authority of the user according to the user identity of the input entry to be viewed;

determining the part which is not displayed in the personnel information according to the viewing authority;

correspondingly, the personnel information in the user viewing authority is displayed during sequential display.

In a preferred embodiment, the generating the ranking number of each personal information with respect to the user includes:

calculating the arrangement serial number of the user according to a calculation formula; wherein the calculation formula is as follows:

m＝a×i+b×j

wherein, a is the weight of the personal relationship map, and b is the weight of the group relationship map; i is the arrangement number of the individual relationship map, b is the arrangement number of the group relationship map, and m is the arrangement number.

In another aspect of the present invention, an address book retrieving apparatus is provided, where the address book includes a plurality of content classifications, the address book retrieving apparatus includes:

the word segmentation splitting module is used for splitting a word to be searched input by a user to obtain a plurality of words; each of the segments belongs to one of the content classifications, and each of the segments contains a multi-dimensional attribute feature; each dimension attribute feature comprises a plurality of different feature contents;

the word segmentation input module is used for inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation between the feature content and the content classification and the probability under each attribute characteristic;

the retrieval combination generation module is used for determining the content classification of each participle based on each corresponding relation and generating a retrieval combination;

and the retrieval module is used for retrieving in the address list based on the retrieval combination.

In a preferred embodiment, the attribute features include:

In a preferred embodiment, further comprising:

the model building module is used for building a plurality of initial decision tree models;

and the model training module is used for training each initial decision tree model by utilizing the query entries classified by the marked word segmentation content to obtain the multiple decision tree models.

In a preferred embodiment, the retrieval combination generating module includes:

the average probability generating unit is used for generating the average probability of all the characteristic contents under each content classification according to each corresponding relation;

and the content classification selecting unit selects the content classification with the maximum corresponding average probability and determines the content classification as the content classification corresponding to the word segmentation.

In a preferred embodiment, the retrieval module includes:

a personnel information retrieval unit for retrieving a plurality of personnel information according with the retrieval combination and under the limited content classification of the retrieval combination;

the serial number determining unit is used for determining a first serial number of each personal information in the personal relation map corresponding to the user and a second serial number in the group relation map according to the user identity of the input entry to be checked;

the arrangement sequence number generating unit generates an arrangement sequence number of each piece of personnel information relative to the user according to the first sequence number and the second sequence number, and the personal relationship map weight and the group relationship map weight corresponding to the user;

and the sequencing display unit is used for sequentially displaying the personnel information to be displayed according to the generated sequencing serial number.

In a preferred embodiment, the retrieval module further comprises:

the permission determining unit is used for determining the viewing permission of the user according to the user identity of the input entry to be checked;

the screening unit is used for determining the part which is not displayed in the personnel information according to the viewing authority;

correspondingly, the sequencing display unit displays the personnel information in the user viewing permission during sequential display.

In a preferred embodiment, the ranking number generation unit calculates the ranking number of the user according to a calculation formula; wherein the calculation formula is as follows:

m＝a×i+b×j

In another aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the address book retrieval method when executing the computer program.

In still another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements a contact list retrieval method.

According to the technical scheme, the address book retrieval method and the address book retrieval device have the advantages that the multi-dimensional attribute characteristics of each participle are obtained by splitting the entry to be retrieved and then are input into the decision tree model, the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, model tuning is continuously performed by combining the machine learning function of the decision tree model, so that manual rule intervention is reduced, basic services of universality and convenience are provided, and the use experience of the system is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart illustrating an address book retrieval method according to an embodiment of the present invention.

Fig. 2 is a detailed flowchart of step S4 in fig. 1.

Fig. 3 is a second flowchart of step S4 in fig. 1.

Fig. 4 is a schematic diagram illustrating screening of personal information in an embodiment of the present invention.

Fig. 5 is a schematic structural diagram of an address book retrieval device according to an embodiment of the present invention.

Fig. 6 is a schematic diagram of a structure of the retrieving module in fig. 5.

Fig. 7 is a second schematic structural diagram of the retrieving module in fig. 5.

Fig. 8 is a schematic diagram of a personal relationship map in an embodiment of the invention.

Fig. 9 is a diagram illustrating a group relationship map according to an embodiment of the present invention.

Fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Considering that the address book in an enterprise is complex, the contact range is changed continuously due to personnel change, the conditions of employee post adjustment, exchange, borrowing and the like are frequently generated, and the conditions of the names of the employees, such as duplicate names, rare words and multi-nationality, are relatively prominent. Firstly, splitting a word to be searched input by a user to obtain a plurality of participles; then inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation between the feature content and the content classification and the probability under each attribute characteristic; determining the content classification of each participle based on each corresponding relation, and generating a retrieval combination; and finally, searching is carried out in the address book based on the searching combination, so that the query purpose of a prediction user is realized, intelligent error correction is realized, more accurate personnel query is provided, meanwhile, model tuning is continuously carried out by combining the machine learning function of the decision tree model, manual rule intervention is reduced, basic service with universality and convenience is provided, and the use experience of the system is improved.

In one or more embodiments of the present invention, as shown in fig. 1, an address book retrieval method, where an address book includes a plurality of content classifications, includes:

s1: splitting a word to be searched strip input by a user to obtain a plurality of participles; each of the segments belongs to one of the content classifications, and each of the segments contains a multi-dimensional attribute feature; each dimension attribute feature includes a plurality of different feature contents.

In the invention, for some enterprise address books, the content classification comprises names, organizational structure names, post names and telephone numbers.

Further, the attribute features include: the character length, the word type and the sequence of the entry to be searched in which the participle is positioned.

Generally, a term to be searched input by a user may be split into 2 or 3 segments, and recognized by a word recognition method, for example, the term to be searched is: suda of the human resources department. Two participles of the human resources department and Suda strong can be identified according to word recognition.

In a preferred embodiment, the word recognition method recognizes the segmented words, which can improve recognition accuracy based on machine learning.

S2: and inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation between the feature content, the content classification and the probability under each attribute characteristic.

Specifically, a plurality of decision tree models are constructed based on a random forest algorithm, and each model comprises a corresponding relation between feature content and content classification and probability under an attribute characteristic.

In the invention, the feature content is each specific representation of the attribute feature, for example, for the attribute feature of character length, the feature content can be 0-8 characters, 9-20 characters and the like, and for the feature content of word type, the feature content can be Chinese characters, letters, numbers and the like.

Through the step S2, the corresponding relationship between the feature content and the content classification under each attribute feature can be obtained, that is, the probability value corresponding to each feature content and each feature content classification can be obtained through a search method.

In some embodiments, the correspondence may be stored in the computer device by a look-up table.

S3: and determining the content classification of each participle based on each corresponding relation, and generating a retrieval combination.

In some specific embodiments, step S3 includes:

s31: and generating the average probability of all the characteristic contents under each content classification according to each corresponding relation.

For example, for "Suda Strong", "Suda Strong" the word type is Chinese, the number of characters is 2-8, for the bar to be looked up: "Suda Strong human resources department", the position is 1.

In the decision tree model, the probability of a kanji under the name content classification is 33%, the probability of characters 0-8 is 65%, and the probability of position 1 is 40%, and the average probability is (33% + 65% + 40%)/3 ═ 138%/3 ═ 46%.

S32: and selecting the content classification with the maximum corresponding average probability to determine the content classification corresponding to the word segmentation.

As another example, if the average probability of "Suzhou-qiang" is 19% for the organization, 27% for the post, and 8% for the phone, the name with the highest probability (46%) is selected as the content category of the participle, and it is concluded that "Suzhou-qiang" is the name. Thus, a search combination can be obtained:

name ═ Suda strength 'and Dept ═ human resource department'

Or

Name ═ Suda strong 'and Org ═ human resource department'

After the condition splitting is completed, the user can be found that the user intends to search for the user named Suda strong under the organization of the human resources department or the user named Suda strong under the organization of the human resources department.

S4: and searching in the address book based on the searching combination.

According to the searching combination, the searching can be carried out in the address book.

In a preferred embodiment, step S4 is not only a search using individual relationship maps, but also a complex search in combination with group relationship maps.

In this embodiment, as shown in fig. 2, step S4 specifically includes:

s41: and retrieving a plurality of personnel information which accord with the content classification limited by the retrieval combination according to the retrieval combination.

Since the enterprise address book includes a large number of heavily-named users, for example, "suda qiang" may include a plurality of users named suda qiang, this step retrieves users that meet each of the word segmentation definition categories.

S42: and determining a first sequence number of each personal information in the personal relationship map corresponding to the user and a second sequence number in the group relationship map according to the user identity of the input entry to be checked.

In the present invention, as shown in fig. 8, the personal relationship graph is created by collecting click objects of users, and the distances of nodes in the personal relationship graph are adjusted according to the communication frequency, and the adjusted personal relationship graph is stored in the cloud or locally.

As shown in fig. 9, the group relationship graph is obtained by combining the clustering algorithm with the individual relationship graph and modifying the individual relationship graph by using the graph clustering detection algorithm.

Specifically, each person information is sorted in the corresponding individual relationship map and the group relationship map according to the relationship distance. The personal relationship map and the group relationship map of the user can be searched.

S43: and generating the arrangement serial number of each piece of personnel information relative to the user according to the first serial number, the second serial number, the personal relationship map weight and the group relationship map weight corresponding to the user.

In some embodiments, the ranking number of the user may be calculated according to a calculation formula; wherein the calculation formula is as follows:

m＝a×i+b×j

For example, user A is the base level manager loan officer community, and for his search result M, the ranking policy is { M } × (personal relationship graph × 0.7.7 + group relationship graph × 0.3). when user A is up-graded as the business headquarters manager decision-maker community, his ranking policy might be adjusted to { M } × (personal relationship graph × 0.2+ group relationship graph × 0.8.8).

S44: and sequentially displaying the information of the persons to be displayed according to the generated serial number.

Through the embodiment, the individual relation map and the group relation map are combined, and the requirement that a single relation map cannot reflect the change of group communication relation after the individual attribute of the user is changed can be well solved.

In a further preferred embodiment, as shown in fig. 3, step S4 further includes:

s45: determining the viewing authority of the user according to the user identity of the input entry to be viewed;

s46: determining the part which is not displayed in the personnel information according to the viewing authority;

correspondingly, step S44 shows the people information in the user' S viewing right when the sequence presentation is performed.

For example, result screening is completed by combining privacy policies inside enterprises, for example, the privacy of high-level managers is protected from being disturbed at will, personal family contact information of employees is protected from being revealed, and the like. The condition information of the staff in the enterprise for privacy protection comprises posts, organizations, departments, jobs and the like. As shown in fig. 4: the left side set is a visible information set of the current user, the right side set is a retrieval result set, and the intersection part (black filling) of the left side set and the right side set is a reserved item after result screening.

In addition, the decision tree model may be established online or offline in the present invention, that is, the step of establishing the model may be included in the implementation step of the present invention, or may be established in advance without departing from the implementation step of the present invention, which is not limited in the present invention.

Specifically, the step of establishing the decision tree model specifically includes:

s01: establishing a plurality of initial decision tree models;

s02: and training each initial decision tree model by using the query entries with the labeled word segmentation content classification to obtain a plurality of decision tree models.

From the above description, it can be seen that the address book retrieval method provided in one aspect of the present invention obtains the multidimensional attribute characteristics of each participle by splitting the entry to be retrieved, and then inputs the characteristics into the decision tree model, so that the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, continuously performs model tuning by combining the machine learning function of the decision tree model, reduces manual rule intervention, provides basic services of universality and convenience, and improves the use experience of the system. Furthermore, in a preferred embodiment, the personal relationship graph and the group relationship graph are combined, so that the relationship network can be automatically adjusted according to the actual working condition of the staff, and the defect of the single-dimensional relationship graph is avoided.

The present invention will be described in detail with reference to specific scenarios.

The system firstly completes query condition assembly by word recognition according to the entry to be searched input by the user. Then classifying each word segmentation input by the user through a random forest algorithm to obtain the most possible combination condition. The method comprises the steps of completing retrieval of information of conforming personnel in a group through conditions to form a result set, then completing information screening based on an authority set, then completing retrieval result sorting, calling association relations in a relation graph to calculate result weights, completing high-low arrangement according to the weights, placing the results which are most compact in relation and most likely to be associated at the top, and completing final result output.

In the generation of the individual relationship map and the group relationship map, the system collects the conditions of the final click result of the user, including the click sequence, the page turning times and the page staying time, and inputs the log into the log analysis device 9. Collecting click conditions of final results, including result retention time, page turning times, click sequence numbers and the like, and adjusting a decision tree result set according to the collected results according to the existing forward records (valve-set inner click) and reverse records (super valve-set click and no click) so as to train random forests; the rule extraction device adjusts the relation model according to the user click probability and the page turning frequency, and dynamically corrects the weight ratio of the current user and the current user according to the group to which the current user belongs.

The system splits the search term and analyzes the search term, wherein the search term comprises attributes such as character type, length, sequence and the like. And then identifying the search terms. The word recognition algorithm adopts a random forest algorithm and carries out recognition according to the attributes of the search words. And combining the identified search terms to finish the precision of the search conditions.

Specifically, assume that there are 3 CART trees (type, length, and sequence) in the forest, the total number of features N is 3, and each CART tree corresponds to a different feature, and the analysis results are shown in table 1:

TABLE 1 CART Tree analysis results Table

CART 1: word type

CART 2: length of

CART 3: sequence of

For example: the user inputs "Suda Strong human resources department" and the analysis results are as follows:

TABLE 2 prediction results of Suda Strong human resources department

Determination of "Suda Strong

Determination of "department of human resources

According to the decision table, the detachable conditions of the Suda Strong manpower resource department are as follows:

name ═ Suda strength 'and Dept ═ human resource department'

Or

Name ═ Suda strong 'and Org ═ human resource department'

And (4) finishing result screening by combining privacy strategies inside enterprises, for example, protecting the privacy of high-level managers from being disturbed at will, protecting personal family contact information of employees from being revealed and the like. The condition information of the staff in the enterprise for privacy protection comprises posts, organizations, departments, jobs and the like. As shown in fig. 6: the left side set is a visible information set of the current user, the right side set is a retrieval result set, and the intersection part of the left side set and the right side set is a reserved item after result screening.

Suppose that a user a has a default ranking number for a search result set M of keywords, and the computation rule of the ranking number M of any element in M is as follows:

m＝a×i+b×j

for example, when the user A is a basic manager loan officer group, the ranking strategy of the user A is { M } × (personal relationship map × 0.7.7 + group relationship map × 0.3.3) ({ M } × (personal relationship map × 0.2.2 + group relationship map × 0.8.8) ("personal relationship map 380.2 +" group relationship map 3638.8) ") for the retrieval result M of the user A, the user A can better solve the requirement that the single relationship map cannot reflect the group communication relationship change after the user individual attribute is changed.

The scene provided by the invention can analyze the input field information of the address book, including names, places, posts, organizations, work contents and other characteristics, predict the query purpose of the user, realize intelligent error correction and provide more accurate personnel query. And the relation network is automatically adjusted according to the actual working condition of the staff, so that the defect of the single-dimensional relation map is avoided. Simultaneously has the following advantages:

1. and identifying the retrieval intention to fulfill the aim of accurate retrieval.

2. Result sorting is carried out through two dimensions of personal relation and group relation, and the scene problem that the relation network of the retrieval result set is invalid due to the change of the personal attributes is effectively solved.

3. Model tuning is continuously carried out through machine learning, manual rule intervention is reduced, basic service of universality and convenience is provided, and use experience of the system is improved.

Based on the same inventive concept, another aspect of the present invention provides an address book retrieving apparatus, where the address book includes a plurality of content classifications, as shown in fig. 5, the address book retrieving apparatus includes:

the word segmentation and separation module 1 is used for splitting a word to be searched input by a user to obtain a plurality of words; each of the segments belongs to one of the content classifications, and each of the segments contains a multi-dimensional attribute feature; each dimension attribute feature comprises a plurality of different feature contents;

the word segmentation input module 2 is used for inputting each word segmentation into a plurality of decision tree models to obtain the corresponding relation between the feature content and the content classification and the probability under each attribute characteristic;

the retrieval combination generating module 3 determines the content classification of each participle based on each corresponding relation and generates a retrieval combination;

and the retrieval module 4 is used for retrieving in the address list based on the retrieval combination.

In a preferred embodiment, the attribute features include:

In a preferred embodiment, further comprising:

In a preferred embodiment, as shown in fig. 6, the retrieving module 4 includes:

a personal information retrieval unit 41 for retrieving a plurality of personal information in accordance with the content classification defined by the retrieval combination according to the retrieval combination;

the sequence number determining unit 42 is used for determining a first sequence number of each personal information in the personal relationship map corresponding to the user and a second sequence number in the group relationship map according to the user identity of the input entry to be checked;

a ranking number generation unit 43 that generates a ranking number of each piece of personal information with respect to the user, based on the first and second numbers, and the personal relationship map weight and the group relationship map weight corresponding to the user;

and the sequencing display unit 44 is used for sequentially displaying the personnel information to be displayed according to the generated sequence number.

In a preferred embodiment, as shown in fig. 7, the retrieving module 4 further includes:

the permission determining unit 45 is used for determining the viewing permission of the user according to the user identity of the input entry to be checked;

the screening unit 46 is used for determining the part which is not displayed in the personnel information according to the viewing authority;

m＝a×i+b×j

Based on the same inventive concept, it can be understood that the address book retrieval device provided by one aspect of the present invention obtains the multidimensional attribute characteristics of each participle by splitting the entry to be retrieved, and then inputs the characteristics into the decision tree model, so that the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, continuously performs model tuning by combining the machine learning function of the decision tree model, reduces manual rule intervention, provides basic services of universality and convenience, and improves the use experience of the system. Furthermore, in a preferred embodiment, the personal relationship graph and the group relationship graph are combined, so that the relationship network can be automatically adjusted according to the actual working condition of the staff, and the defect of the single-dimensional relationship graph is avoided.

In terms of hardware, in order to provide an embodiment of the electronic device for implementing all or part of the contents in the address book retrieval method, the electronic device specifically includes the following contents:

a processor (processor), a memory (memory), a communication Interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the communication interface is used for realizing information transmission among related equipment such as a server, a device, a distributed message middleware cluster device, various databases, a user terminal and the like; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may refer to the embodiment of the address book retrieval method in the embodiment and the embodiment of the address book retrieval apparatus for implementation, and the contents thereof are incorporated herein, and repeated details are not repeated.

Fig. 10 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present invention. As shown in fig. 10, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 10 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.

In one embodiment, the address book retrieval function may be integrated into the cpu 9100. For example, the central processor 9100 may be configured to control as follows:

S4: and searching in the address book based on the searching combination.

As can be seen from the above description, the electronic device provided in the embodiment of the present invention obtains the multidimensional attribute characteristics of each participle by splitting the to-be-searched vocabulary entry, and then inputs the obtained characteristics into the decision tree model, so that the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, continuously performs model tuning by combining the machine learning function of the decision tree model, reduces manual rule intervention, provides basic services of universality and convenience, and improves the use experience of the system.

In another embodiment, the address book retrieving device may be configured separately from the central processing unit 9100, for example, the address book retrieving device may be configured as a chip connected to the central processing unit 9100, and the address book retrieving function is realized under the control of the central processing unit.

As shown in fig. 10, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 10; in addition, the electronic device 9600 may further include components not shown in fig. 10, which can be referred to in the prior art.

As shown in fig. 10, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.

The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.

The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.

The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing ordinary telecommunications functions. The audio processor 9130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100, thereby enabling recording locally through the microphone 9132 and enabling locally stored sounds to be played through the speaker 9131.

An embodiment of the present invention further provides a computer-readable storage medium capable of implementing all the steps of the address book retrieval method in which an execution subject in the above embodiment may be a server, where the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements all the steps of the address book retrieval method in the above embodiment.

As can be seen from the above description, the computer-readable storage medium provided in the embodiments of the present invention obtains the multidimensional attribute characteristics of each participle by splitting the entry to be searched, and then inputs the characteristic characteristics into the decision tree model, so that the decision tree model predicts the query purpose of the user, realizes intelligent error correction, provides more accurate personnel query, and meanwhile, continuously performs model tuning in combination with the machine learning function of the decision tree model, reduces manual rule intervention, provides basic services of universality and convenience, and improves the use experience of the system.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims

1. An address book retrieval method, wherein the address book includes a plurality of content classifications, the address book retrieval method comprising:

and searching in the address book based on the searching combination.

2. The address book retrieval method of claim 1, wherein the content classification comprises: name, organization name, post name, telephone number.

3. The address book retrieval method of claim 1, wherein the attribute features comprise:

4. The address book retrieval method of claim 1, further comprising:

establishing a plurality of initial decision tree models;

5. The address book retrieval method of claim 1, wherein the determining the content classification to which each word segmentation belongs based on each correspondence comprises:

6. The address book retrieval method of claim 1, wherein the retrieving in the address book based on the retrieval combination comprises:

7. The address book retrieval method of claim 6, wherein retrieving in the address book based on the retrieval combination further comprises:

8. The address book retrieval method of claim 6, wherein the generating of the serial number of each personal information with respect to the user comprises:

m＝a×i+b×j

9. An address book retrieval device, wherein the address book includes a plurality of content classifications, the address book retrieval device comprising:

10. The address book retrieval device of claim 9, wherein the content classification comprises: name, organization name, post name, telephone number.

11. The address book retrieval device of claim 9, wherein the attribute feature comprises:

12. The address book retrieval device of claim 9, further comprising:

13. The address book retrieval device of claim 9, wherein the retrieval combination generation module comprises:

14. The address book retrieval device of claim 9, wherein the retrieval module comprises:

15. The address book retrieval device of claim 14, wherein the retrieval module further comprises:

16. The address book retrieval device of claim 14, wherein the arrangement number generation unit calculates the arrangement number of the user according to a calculation formula; wherein the calculation formula is as follows:

m＝a×i+b×j

17. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the address book retrieval method of any one of claims 1 to 8 when executing the program.

18. A computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the address book retrieval method according to any one of claims 1 to 8.