CN115563252A

CN115563252A - Method, system, device and computer readable storage medium for searching service intention

Info

Publication number: CN115563252A
Application number: CN202210949028.4A
Authority: CN
Inventors: 张岩超
Original assignee: Kangjian Information Technology Shenzhen Co Ltd
Current assignee: Kangjian Information Technology Shenzhen Co Ltd
Priority date: 2022-08-09
Filing date: 2022-08-09
Publication date: 2023-01-03

Abstract

The invention provides a method, a system, equipment and a computer readable storage medium for searching a business intention, wherein the method comprises the following steps: receiving a retrieval appeal; if the received search demand is detachable, splitting the search demand into a plurality of vocabularies, and identifying the part of speech of each vocabulary; setting part-of-speech priority for each vocabulary, and matching retrieval weights corresponding to the priorities for different part-of-speech priorities; detecting that vocabularies provided with active tags or passive tags exist in the retrieval appeal with the part of speech priority, and if the vocabularies provided with the active tags exist, improving the retrieval weight of the retrieval sentences containing the active tags; if the vocabulary with the passive tags exists, the retrieval weight of the retrieval statement containing the passive tags is improved; and calling a search engine to retrieve the retrieval statement so as to obtain a retrieval intention matched with the retrieval appeal. The invention analyzes the real retrieval intention of the user, improves the retrieval accuracy of the user, the search utilization rate and the rationality of the search result.

Description

Method, system, device and computer readable storage medium for searching service intention

Technical Field

The invention belongs to the technical field of internet search, relates to a method and a system, and particularly relates to a method, a system, equipment and a computer readable storage medium for searching a business intention.

Background

With the vigorous development of the internet industry, accurate data marketing can provide strong support for the development of enterprises. Under the concept of data marketing, a search module becomes an effective means for improving the user experience and direct conversion, and in the search in the industry, at the stage of identifying the user intention convenience in a relatively primary stage, an excellent insurance business search intention identification algorithm can improve the boosting for the sale of insurance products and the retention of users on apps.

The existing industry search intention identification is deficient:

1, no intention identification can be made for specific, e.g. insurance, industries:

for example: when a user searches for ' e ' and ' e ' to generate a guarantee ', a traditional search engine can display data containing three words of ' e ', generation and ' guarantee ', the data is very messy, and even a result containing only one word can be retrieved.

2, the accurate retrieval cannot be carried out according to the specific requirements of the user:

for example: the user retrieves "children-appropriate insurance", and the traditional search engine only recognizes "insurance", but cannot recognize the retrieval requirement of the user for a specific crowd such as "children".

For the above-mentioned common problem of search intention identification in the insurance industry, if the use of the user is directly influenced, it is required to know that the search behavior of the user is generally with an accurate purpose, and products and information meeting personal appeal are to be quickly found through search. A search engine that cannot accurately identify intent would be a failed product.

Therefore, how to provide a method, a system, a device and a computer readable storage medium for searching a business intention to solve the defects that the prior art cannot meet the specific requirements of users and the searching product is not accurate has become a technical problem to be urgently solved by those skilled in the art.

Disclosure of Invention

In view of the above drawbacks of the prior art, an object of the present invention is to provide a method, a system, a device and a computer-readable storage medium for searching business intents, which are used to solve the problem that the prior art cannot perform accurate search according to user-specific requirements.

To achieve the above and other related objects, in a first aspect, the present invention provides a method for retrieving a business intention, including:

receiving a retrieval demand to be retrieved; the search appeal comprises a vocabulary for searching the business intention;

if the received search demand is detachable, splitting the search demand into a plurality of vocabularies, collecting and identifying the parts of speech of each vocabulary;

setting part-of-speech priority for each vocabulary, and matching retrieval weights corresponding to the priorities for different part-of-speech priorities;

detecting that a vocabulary with an active tag or a passive tag exists in the retrieval appeal with the part of speech priority, if the vocabulary with the active tag exists, retrieving the retrieval statement containing the active tag, and improving the retrieval weight of the retrieval statement containing the active tag; if the vocabulary with the passive tags exists, retrieving the retrieval sentences containing the passive tags, and improving the retrieval weight of the retrieval sentences containing the passive tags; the method comprises the steps that active tags are configured for passively received vocabularies, and passive tags are configured for actively recognized vocabularies;

and preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain the retrieval intention matched with the retrieval appeal.

In a second aspect, the present invention provides a system for retrieving a business intention, comprising:

the receiving module is used for receiving the search appeal to be searched; the search appeal including a vocabulary for searching for a search intent;

the language processing module is used for splitting the received search appeal into a plurality of vocabularies and collecting and identifying the part of speech of each vocabulary when the received search appeal is detachable;

the priority setting module is used for setting part-of-speech priority for each vocabulary and matching retrieval weight corresponding to the part-of-speech priority for different part-of-speech priorities;

the retrieval execution module is used for detecting that vocabularies provided with active tags or passive tags exist in the retrieval appeal after the part of speech priority is set, retrieving the retrieval sentences containing the active tags if the vocabularies provided with the active tags exist, and improving the retrieval weight of the retrieval sentences containing the active tags; if the vocabulary with the passive tags exists, retrieving the retrieval sentences containing the passive tags, and improving the retrieval weight of the retrieval sentences containing the passive tags; preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain a retrieval intention matched with the retrieval demand;

wherein, an active tag is configured for the passively received vocabulary, and a passive tag is configured for the actively recognized vocabulary.

In a third aspect, the present invention provides a computer-readable storage medium, which stores a computer program, wherein the computer program is configured to implement the steps of the method for retrieving the service intention when executed by a processor.

In a fourth aspect, the present invention provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for retrieving the business intent.

As described above, the service identification method/system, the service retrieval method/system, the medium and the device according to the present invention have the following advantages:

the method, the system, the equipment and the computer readable storage medium for retrieving the service intention analyze the real retrieval intention of the user, provide basic labels and part-of-speech classification for the next retrieval of a search engine, and are beneficial to improving the retrieval accuracy of the user. The invention can acquire the core vocabulary retrieved by the user, match the related labels of the products and display the related products and information, can meet the effective user retrieval of services in various fields, and obviously improves the search utilization rate and the rationality of the search result.

Drawings

Fig. 1A is a flowchart illustrating a detailed implementation of a business intention retrieval method according to an embodiment of the invention.

Fig. 1B is a schematic flow chart of S17 in the method for retrieving a business intention according to the present invention.

FIG. 2 is a schematic structural diagram of a business intent retrieval system according to an embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Description of the element reference

2. Retrieval system of business intention

21. Receiving module

22. Language processing module

23. Classified storage module

24. Filtering module

25. Priority setting module

26. Retrieval execution module

S11 to S19

Detailed Description

The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, amount and proportion of each component in actual implementation may be changed freely, and the layout of the components may be complicated.

Example one

The embodiment provides a business intention retrieval method, which comprises the following steps:

receiving a retrieval appeal; the search appeal comprises a vocabulary for searching the business intention;

if the received search appeal is detachable, splitting the search appeal into a plurality of vocabularies, collecting and identifying the part of speech of each vocabulary;

and preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain the retrieval intention matched with the retrieval demand.

The method for retrieving the service intention provided by the present embodiment will be described in detail with reference to the drawings. The method for searching the service intention can be applied to various target industry fields, and the real service intention of the user can be accurately searched by analyzing the search complaint input by the user. The service identification method according to the embodiment is applied to the field of insurance industry and will be described in detail below.

Please refer to fig. 1A, which is a flowchart illustrating an embodiment of a service intention retrieval method according to an embodiment of the present invention. As shown in fig. 1A, the service identification method specifically includes the following steps:

and S11, receiving the search demand. In the embodiment, the search appeals comprise words for searching the business intentions.

For example, the received search appeal is "insurance suitable for children to purchase".

S12, whether the received search appeal is detachable is detected. If yes, executing the S13; if not, S14 is executed, namely the search appeal which cannot be split is collected.

And S13, splitting the received search demand into a plurality of vocabularies, and collecting the split vocabularies.

In this embodiment, the S12 performs the splitting detection and the splitting processing on the received language data by using a trained natural language processing component related to an industry field.

The natural language processing component is, for example, "HanLP". HanLP is a Java toolkit consisting of a series of models and algorithms aimed at facilitating the application of natural language processing in a production environment. The method supports Chinese word segmentation (N-shortest path word segmentation, CRF word segmentation, index word segmentation, user-defined dictionary and part-of-speech tagging), named entity identification (person name, transliterated person name, place name and entity organization name identification), keyword extraction, automatic summarization, phrase extraction, pinyin conversion, simple and complex conversion, text recommendation, dependency syntactic analysis (MaxEnt dependency syntactic analysis and neural network dependency syntactic analysis) and the like.

For example, when the input language data is "insurance suitable for children's purchase", the natural language processing component "HanLP" splits "insurance suitable for children's purchase" into: five separable vocabularies suitable for children, purchasing and insurance. And S14, if the received language data is not detachable, collecting non-detachable words, for example, when the natural language processing component HanLP receives the language data which is not detachable, such as i Kangbao million medical treatment chronic disease edition, i Kangbao million medical treatment (chronic disease edition), chronic disease edition, million medical treatment, old edition, upgraded edition and the like, collecting the language data into the non-detachable words.

For example, after the received search appeals "e sha bao" - > "e", "sha", "bao", and "e sha bao", the insurance-specific vocabulary of "e sha bao" will not be split, and the corpus searched by the search engine will be the reasonable segmentation after the intention is identified. The search result will only be related to "e-Save", and no invalid entries containing "e", "Save" and "Save" will be searched.

In this embodiment, the non-separable language data can be passively received (i.e. manually input by a service person in the related industry field) or actively recognized by a service recognition system.

S15, the collected vocabularies (namely, the splittable vocabularies and the non-splittable vocabularies) are classified and stored into the splittable vocabularies related to the target industry field and the non-splittable vocabularies related to the target industry field, and the parts of speech of the splittable vocabularies and the non-splittable vocabularies are recognized. In the present embodiment, the parts of speech recognized include parts of speech of words including verbs, nouns, vernouns, numerals, and dummy words.

For example, "insurance suitable for children's purchase" is broken down into: the five detachable vocabularies suitable for children, buying, insurance are classified into detachable vocabularies related to the insurance industry field.

For example, non-separable vocabularies such as itangbao million medical chronic disease edition, itangbao million medical (chronic disease edition), chronic disease edition, million medical treatment, aged edition, upgraded edition, and the like are classified into non-separable vocabularies related to the insurance industry field.

For example, the parts of speech of the five divided words, which are proper, children, purchasing and insurance, are sequentially recognized, that is, the part of speech of "proper" is a verb, the part of speech of "children" is a noun, the part of speech of "purchasing" is a verb, the part of speech of "is an assistant word, and the part of speech of" insurance "is a noun.

For example, the non-resolvable vocabulary "i kang Bao million medical lenti instances" is identified as the proper vocabulary in the noun.

And S16, filtering the split virtual words (the virtual words comprise adverbs, prepositions, conjunctions, auxiliary words and the like).

For example, the word "help words" split from "insurance suitable for children's purchase" is filtered.

S17, setting part-of-speech priority for each vocabulary, and matching retrieval weight corresponding to the part-of-speech priority for different part-of-speech priorities.

Specifically, the step S17 includes setting part-of-speech priorities for both the dividable vocabulary and the non-dividable vocabulary.

In the present embodiment, please refer to fig. 1B, which is a flowchart of S17, in order to better identify the search intention of the user. As shown in fig. 1B, the S17 specifically includes:

s171, setting nouns and noun verbs as first priority vocabularies, setting names, geographic related vocabularies, organization groups and special vocabularies in the verbs and the nouns as second priority vocabularies, setting adjectives as third priority vocabularies and setting numerators as fourth priority vocabularies.

S172, the retrieval weight which is the highest in matching of the first priority vocabulary, the retrieval weight which is the second highest in matching of the second priority vocabulary is reset to be the second highest, the retrieval weight which is the third lowest in matching of the third priority vocabulary and the retrieval weight which is the lowest in matching of the fourth priority vocabulary.

For example, the related vocabulary of insurance business: the noun "life insurance" is set as a first-level vocabulary, the noun verb "claim" is set as a first-level vocabulary, the abbreviation "three-high" is set as a first-priority vocabulary, the name "old age" indicating time is set as a first-priority vocabulary, the name/place name/organization group is set as a second-priority vocabulary, and the proper noun "face cleaning" is set as a second-priority vocabulary.

For example, the S17 sets "fit" of the split vocabulary after splitting "fit for child purchase" as a second-priority vocabulary, sets "child" as a first-priority vocabulary, sets "purchase" as a second-priority vocabulary, sets "insurance" as a first-priority vocabulary, and assigns the highest retrieval weight to "child" and "insurance", for example, assigns 1.5 as the highest retrieval weight, and assigns the next highest retrieval weight to "fit" and "purchase", for example, assigns 1.2 as the next highest retrieval weight.

S18, detecting that vocabularies with active tags or passive tags exist in the retrieval appeal after the part of speech priority is set, if the vocabularies with the active tags exist, retrieving the retrieval sentences containing the active tags, and improving the retrieval weight of the retrieval sentences containing the active tags; and if the vocabulary with the passive tags exists, searching the search sentences containing the passive tags, and improving the search weight of the search sentences containing the passive tags. The method comprises the steps that active tags are configured for passively received vocabularies, and passive tags are configured for actively recognized vocabularies;

in this embodiment, an active tag is configured for a passively received vocabulary, and a passive tag is configured for an actively recognized vocabulary; the active tag is a manually defined attribute which is obtained by operator according to the characteristics of the retrieval result. The passive tag is the self attribute of the retrieval result.

For example, the words allocated with the active tags include cancer hospitalization overseas, hospital reservation, translation, economy class, transportation fees, overseas lodging fees, interstellar hotels and the like, the words allocated with the passive tags include families, children, overseas high-end medical treatment, transportation lodging and the like, and the insurance products searched for to be suitable for the words are anti-cancer guardian overseas versions.

Specifically, the step of retrieving the search statement including the active tag in S18 and raising the search weight of the search statement including the active tag includes: when the active tag is retrieved, weighting the retrieval weight of the matched active tag; the steps of retrieving the retrieval statement containing the passive tag and promoting the retrieval weight of the retrieval statement containing the passive tag comprise: and when the passive label is retrieved, weighting the retrieval weight of the matched passive label.

In this embodiment, the step of weighting the search weight of the matched active tag includes: and multiplying the retrieval weight of the matched active tag by the highest retrieval weight of the first priority vocabulary matching.

In this embodiment, the step of weighting the search weights of the matched passive tags includes: multiplying the search weight of the matched passive tag by the next highest search weight of the second priority vocabulary match.

For example, the active tag of "child" is retrieved, the retrieval weight of insurance products matched with the tag of "child" is multiplied by the retrieval weight with the highest matching first priority vocabulary, for example, 1.5 times the retrieval weight with the highest matching first priority vocabulary, the passive tag is multiplied by the retrieval weight with the next highest matching second priority vocabulary, for example, 1.2 times the retrieval weight with the next highest matching second priority vocabulary, and the result is that the relevance score is multiplied by the weighting of the tag improvement according to the search index, so that the retrieval accuracy can be obviously improved.

And S19, preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain the retrieval intention matched with the retrieval appeal.

In this embodiment, in S19, the search weights are ranked in descending order by default, and the higher the ranking, the more relevant the search intention of the user.

The retrieval method of the business intention analyzes the real retrieval intention of the user, provides basic labels and part-of-speech classification for the next retrieval of the search engine, and is beneficial to improving the accuracy of the retrieval of the user. The invention can acquire the core vocabulary retrieved by the user, match the related labels of the products and display the related products and information, can meet the effective user retrieval of services in various fields, and obviously improves the search utilization rate and the rationality of the search results.

The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the method for retrieving the business intent as shown in fig. 1A, the computer program, when being executed by the processor, implementing the following steps:

receiving language data to be retrieved; the language data comprises words for retrieving the business intent;

if the received language data can be split, splitting the language data into a plurality of vocabularies, collecting and identifying the parts of speech of each vocabulary;

detecting that words with active tags or passive tags exist in the language data with the part of speech priority, if the words with the active tags exist, retrieving the retrieval sentences containing the active tags, and improving the retrieval weight of the retrieval sentences containing the active tags; if the vocabulary with the passive tags exists, searching the search sentences containing the passive tags, and improving the search weight of the search sentences containing the passive tags; the method comprises the steps that active tags are configured for passively received vocabularies, and passive tags are configured for actively recognized vocabularies;

and preferentially displaying according to the size of the promoted retrieval weight so as to obtain the retrieval intention of the user.

The present application may be embodied as systems, methods, and/or computer program products, in any combination of technical details. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present application.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as a punch card or an in-groove protrusion structure having instructions stored thereon, and any suitable combination of the foregoing. A computer-readable storage medium as used herein is not to be interpreted as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

The computer-readable programs described herein may be downloaded from a computer-readable storage medium to a variety of computing/processing devices, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device. The computer program instructions for carrying out operations of the present application may be assembly instructions, instruction Set Architecture (ISA) instructions, machine related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present application are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Example two

The embodiment further provides a system for retrieving a business intention, which includes:

a receiving module for receiving the search appeal; the search appeal includes a vocabulary for searching for a search intent;

the language processing module is used for splitting the received search appeal into a plurality of vocabularies and collecting and identifying the part of speech of each vocabulary if the received search appeal is separable;

the retrieval execution module is used for detecting that vocabularies provided with active tags or passive tags exist in the retrieval appeal after the part of speech priority is set, retrieving retrieval sentences containing the active tags if the vocabularies provided with the active tags exist, and improving the retrieval weight of the retrieval sentences containing the active tags; if the vocabulary with the passive tags exists, retrieving the retrieval sentences containing the passive tags, and improving the retrieval weight of the retrieval sentences containing the passive tags; preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain a retrieval intention matched with the retrieval appeal;

The retrieval system of the business intention provided by the present embodiment will be described in detail with reference to the drawings. Please refer to fig. 2, which is a schematic structural diagram of a service intention retrieval system in an embodiment. As shown in fig. 2, the retrieval system 2 of the business intention includes a receiving module 21, a language processing module 22, a classification storage module 23, a filtering module 24, a priority setting module 25 and a retrieval execution module 26.

The receiving module 21 is configured to receive a search solicitation. In this embodiment, the search solicitation includes a vocabulary for searching the business intent.

The language processing module 22 is used to detect whether the received search appeal is detachable. If so, splitting the received search demand into a plurality of vocabularies, and collecting the split vocabularies; if not, collecting the search appeal which cannot be split.

In one embodiment, the language processing module 22 processes the received search query using trained and industry-related natural language processing components.

The natural language processing component is, for example, "HanLP". HanLP is a Java toolkit composed of a series of models and algorithms aimed at facilitating the application of natural language processing in a production environment. The method supports Chinese word segmentation (N-shortest path word segmentation, CRF word segmentation, index word segmentation, user-defined dictionary and part-of-speech tagging), named entity identification (person name, transliterated person name, place name and entity organization name identification), keyword extraction, automatic summarization, phrase extraction, pinyin conversion, simple and complex conversion, text recommendation, dependency syntactic analysis (MaxEnt dependency syntactic analysis and neural network dependency syntactic analysis) and the like.

In this embodiment, the non-detachable search appeal can be passively received (i.e., manually input by service personnel in the relevant industry field) or actively identified by a service identification system.

In one embodiment, the language processing module 22 is further configured to identify parts of speech of the splittable vocabulary and the non-splittable vocabulary. In the present embodiment, the parts of speech recognized include parts of speech of words including verbs, nouns, vernouns, numerals, and fictitious words.

The classification storage module 23 is configured to store the collected vocabularies (i.e., the splittable vocabulary and the non-splittable vocabulary) as splittable vocabularies related to the target industry field and non-splittable vocabularies related to the target industry field in a classification manner.

The filtering module 24 is configured to filter the split fictitious words (the fictitious words include adverbs, prepositions, conjunctions, and auxiliary words).

The priority configuration module 25 is configured to set part-of-speech priority for each vocabulary, and match the retrieval weight corresponding to the part-of-speech priority for different part-of-speech priorities.

Specifically, the priority configuration module 25 is configured to set part-of-speech priorities for each of the detachable vocabulary and the non-detachable vocabulary.

In one embodiment, in order to better identify the search intention of the user, the priority configuration module 25 is configured to set the nouns and the noun verbs as a first priority vocabulary, set the verbs and the names of the people, the geographically related vocabularies, the organization groups, and the private vocabularies in the nouns as a second priority vocabulary, set the adjectives as a third priority vocabulary, and set the numerators as a fourth priority vocabulary; the highest retrieval weight is matched for the first priority vocabulary, the retrieval weight of the second priority vocabulary matched with the second highest is set as the second highest, the third priority vocabulary is matched with the retrieval weight of the lower level, and the fourth priority vocabulary is matched with the retrieval weight of the lowest level.

The retrieval execution module 26 is configured to detect that a vocabulary with an active tag or a passive tag exists in the retrieval requirement after the part-of-speech priority is set, retrieve a retrieval statement including the active tag if the vocabulary with the active tag exists, and enhance a retrieval weight of the retrieval statement including the active tag; if the vocabulary with the passive tags exists, retrieving the retrieval sentences containing the passive tags, and improving the retrieval weight of the retrieval sentences containing the passive tags; the method comprises the steps that active tags are configured for passively received vocabularies, and passive tags are configured for actively recognized vocabularies;

In one embodiment, specifically, when there is a vocabulary with active tags in the search appeal after the part of speech priority is set, the step of the search execution module 26 raising the search weight of the search statement including the active tags includes: when the active label is retrieved, weighting the retrieval weight of the matched active label; when the vocabulary with the passive tag exists in the search appeal after the part of speech priority is set, the step of increasing the search weight of the search appeal including the passive tag by the search execution module 26 includes: and when the passive label is retrieved, weighting the retrieval weight of the matched passive label.

Specifically, the weighting the search weight of the matched active tag by the search execution module 26 is: and multiplying the retrieval weight of the matched active tag by the highest retrieval weight matched by the first priority vocabulary.

The step of weighting the search weight of the matched passive tag by the search execution module 26 is: multiplying the search weight of the matched passive tag by the next highest search weight of the second priority vocabulary match.

The retrieval executing module 26 is further configured to preferentially display the retrieval statements corresponding to the promoted retrieval weight according to the size of the retrieval weight, and invoke a search engine to retrieve the retrieval statements so as to obtain a retrieval intention matching the retrieval appeal.

In this embodiment, the search execution module 26 is configured to default to rank the search results in descending order of the search weight, and rank the higher the rank, the more relevant the search intention of the user.

It should be noted that the division of the modules of the above system is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity or may be physically separated. And the modules can be realized in a form that all software is called by the processing element, or in a form that all the modules are realized in a form that all the modules are called by the processing element, or in a form that part of the modules are called by the processing element. For example: the x module can be a separately established processing element, and can also be integrated in a certain chip of the system. In addition, the x module may also be stored in the memory of the system in the form of program codes, and may be called by one of the processing elements of the system to execute the functions of the x module. Other modules are implemented similarly. All or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by the integrated logic circuit of hardware in the processor element or instructions in the form of software. These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors (DSPs), one or more Field Programmable Gate Arrays (FPGAs), and the like. When a module is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. These modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).

EXAMPLE III

In this embodiment, a computer device is provided, and the computer device may be a server, and its internal structure diagram may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes non-volatile and/or volatile storage media, internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external client through a network connection. The computer program is executed by a processor to implement the functions or steps of the service side of a business intention retrieval method.

In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:

receiving a search appeal; the search solicitation comprises a vocabulary used for searching the service intention;

the search sentences corresponding to the enhanced search weight are preferentially displayed according to the size of the enhanced search weight, a search engine is called to search the search sentences to obtain the search intention matched with the search appeal, the protection range of the search method for the business intention is not limited to the execution sequence of the steps listed in the embodiment, and all the schemes of increasing and decreasing the steps and replacing the steps in the prior art according to the principle of the invention are included in the protection range of the invention.

The invention also provides a business intention retrieval system, which can implement the business intention retrieval method of the invention, but the implementation device of the business intention retrieval method of the invention includes but is not limited to the structure of the business intention retrieval system listed in the embodiment, and all structural modifications and substitutions of the prior art made according to the principle of the invention are included in the protection scope of the invention.

In summary, the service identification system, the retrieval method based on the service identification system, the storage medium and the device of the invention analyze the real retrieval intention of the user, provide basic labels and part-of-speech classification for the next retrieval of the search engine, and are beneficial to improving the accuracy of the user retrieval. The invention can acquire the core vocabulary retrieved by the user, match the related labels of the products and display the related products and information, can meet the effective user retrieval of services in various fields, and obviously improves the search utilization rate and the rationality of the search results. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which may be accomplished by those skilled in the art without departing from the spirit and scope of the present invention as set forth in the appended claims.

Claims

1. A method for retrieving a business intention, comprising:

receiving a search appeal; the search appeal comprises a vocabulary for searching the business intention;

setting part-of-speech priority for each vocabulary, and matching retrieval weights corresponding to the part-of-speech priority for different part-of-speech priorities;

2. The method for retrieving service intention according to claim 1, wherein after receiving the retrieval appeal to be retrieved, the method further comprises: if the received search appeal is not detachable, the search appeal which is not detachable is collected, and the collected vocabularies are classified and stored into detachable vocabularies relevant to the target industry field and non-detachable vocabularies relevant to the target industry field.

3. The method of claim 2, wherein the setting of part-of-speech priority for each vocabulary and the setting of matching search weights for different part-of-speech priorities further comprises setting of part-of-speech priority for both separable vocabularies and non-separable vocabularies.

4. The method for retrieving a business intent according to claim 1,

the part of speech of the vocabulary comprises verbs, nouns, dynamic nouns, digital words and virtual words;

the method for setting part-of-speech priority for each vocabulary and matching the retrieval weight corresponding to the part-of-speech priority for different part-of-speech priorities comprises the following steps:

setting nouns and name verbs as first priority vocabularies, setting the verbs and names, geographic related vocabularies, organization groups and special vocabularies in the nouns as second priority vocabularies, setting adjectives as third priority vocabularies and setting numerics as fourth priority vocabularies;

matching the highest retrieval weight for the first priority vocabulary, matching the second priority vocabulary with the next highest retrieval weight, matching the third priority vocabulary with the lower retrieval weight, and matching the fourth priority vocabulary with the lowest retrieval weight.

5. The method of claim 4, wherein before setting part-of-speech priority for each vocabulary and matching the different part-of-speech priorities with the search weights corresponding to the priorities, the method further comprises: and filtering the split fictitious words.

6. The method for retrieving a business intent according to claim 4,

the steps of retrieving the retrieval statement containing the active tag and promoting the retrieval weight of the retrieval statement containing the active tag comprise: when the active tag is retrieved, weighting the retrieval weight of the matched active tag;

the steps of retrieving the retrieval statement containing the passive tag and promoting the retrieval weight of the retrieval statement containing the passive tag comprise: and when the passive label is retrieved, weighting the retrieval weight of the matched passive label.

7. The method for retrieving a business intent according to claim 6,

the step of weighting the retrieval weight of the matched active tag comprises the following steps: multiplying the retrieval weight of the active tag by the highest retrieval weight matched with the first priority vocabulary;

the step of weighting the retrieval weight of the matched passive label comprises the following steps: multiplying the search weight of the passive tag by the next highest search weight of the second priority vocabulary match.

8. A system for retrieving a business intent, comprising:

the receiving module is used for receiving the search appeal to be searched; the search appeal includes a vocabulary for searching for a search intent;

the retrieval execution module is used for detecting that vocabularies provided with active tags or passive tags exist in the retrieval appeal after the part of speech priority is set, retrieving retrieval sentences containing the active tags if the vocabularies provided with the active tags exist, and improving the retrieval weight of the retrieval sentences containing the active tags; if the vocabulary with the passive tags exists, retrieving the retrieval sentences containing the passive tags, and improving the retrieval weight of the retrieval sentences containing the passive tags; preferentially displaying the retrieval sentences corresponding to the promoted retrieval weight according to the size of the promoted retrieval weight, and calling a search engine to retrieve the retrieval sentences so as to obtain a retrieval intention matched with the retrieval demand;

9. A computer-readable storage medium, in which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for retrieving a business intention according to any one of claims 1 to 7.

10. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the computer program, when executed by the processor, carries out the steps of the method for retrieving a business intent according to any one of claims 1 to 7.