CN112162955A

CN112162955A - User log processing device and method

Info

Publication number: CN112162955A
Application number: CN202011180314.6A
Authority: CN
Inventors: 邵星阳; 杨善松; 刘永霞
Original assignee: Hisense Visual Technology Co Ltd
Current assignee: Hisense Visual Technology Co Ltd
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2021-01-01

Abstract

The application provides a processing device and a method of a user log, comprising the following steps: a processor configured to: acquiring a user log, and determining a first query statement in the user log, wherein the first query statement is a query statement which is determined to be abnormal through the whole life cycle of the user query statement analyzed by a semantic engine, and/or a query statement with an abnormal result fed back by the semantic engine; determining a new requirement based on the first query statement; and optimizing the current semantic engine based on the new requirement so that the semantic engine supports the business positioning of the new requirement and the business processing of the new requirement. The new requirements of the user are mined from the abnormal query sentences in the user log, and the semantic engine is optimized, so that the service capability of the semantic engine is improved, the semantic engine can accurately provide services for the user, and the user experience is improved.

Description

User log processing device and method

Technical Field

The present application relates to the field of computer technologies, and in particular, to a device and a method for processing a user log.

Background

The natural language processing technology is widely applied to smart home. Specifically, the user can control the smart home through voice. For example, a user can request content on a smart television through voice query; correspondingly, the intelligent television identifies the voice, generates corresponding text content (namely query statement), sends the text content to the server, and a semantic engine deployed by the server performs text analysis on the query statement and positions corresponding services, so that a corresponding query result is fed back to the user.

However, in practical applications, situations that a semantic engine fails to analyze or support a query statement of a user, or a feedback result does not meet a user requirement, etc. easily occur, so that a service cannot be accurately provided for the user, and user experience is poor.

Disclosure of Invention

The application provides a user log processing device and method, which aim to solve the problems that in the related technology, a semantic engine cannot analyze or support a query statement of a user, or a feedback result does not meet the requirements of the user, and the like, so that the user cannot be accurately provided with services, the user experience is poor, and the like.

A first aspect of the present application provides a device for processing a user log, including: a processor;

the processor configured to:

acquiring a user log, and determining a first query statement in the user log, wherein the first query statement is a query statement which is determined to be abnormal through the whole life cycle of the user query statement analyzed by a semantic engine, and/or a query statement with an abnormal result fed back by the semantic engine;

determining a new requirement based on the first query statement;

and optimizing the current semantic engine based on the new requirement so that the semantic engine supports the business positioning of the new requirement and the business processing of the new requirement.

In some embodiments of the present application, the processor is further configured to:

determining the occurrence frequency corresponding to each first query statement;

the treatment appliance is configured to:

clustering the first query sentences to obtain first query sentences included in each cluster;

aiming at each cluster, determining a requirement name corresponding to the cluster according to each first query statement in the cluster and the occurrence frequency corresponding to each first query statement;

and determining new requirements based on the requirement names corresponding to the clusters.

In some embodiments of the present application, the treatment appliance is configured to:

acquiring a target query statement in a user log;

and preprocessing the target query statement to obtain a first query statement and the occurrence frequency corresponding to each first query statement, wherein the first query statements are not repeated.

extracting a second query statement which cannot be analyzed or not supported by a semantic engine and/or a third query statement of which the semantic engine feedback result does not meet the user requirement from the user log according to a preset extraction rule;

taking the second query statement and/or the third query statement as the target query statement.

counting the target query sentences to obtain the same occurrence times of the target query sentences;

and de-duplicating the target query statement to obtain a non-repeated target query statement as the first query statement.

generating sentence vectors corresponding to the first query sentences according to a preset generation rule;

and clustering the first query sentences based on a preset clustering algorithm and sentence vectors corresponding to the first query sentences to obtain the first query sentences included in each cluster.

In some embodiments of the present application, the processor is further configured to: determining a first keyword corresponding to each cluster according to a first query statement included in each cluster;

the treatment appliance is configured to: and aiming at each cluster, determining a requirement name corresponding to the cluster according to the first query statement with the largest occurrence frequency of the cluster and the first keyword corresponding to the cluster.

for each cluster, performing word segmentation on each first query statement included in the cluster, and performing screening processing according to a preset screening rule to obtain a group of words corresponding to the cluster;

and extracting a first keyword corresponding to the cluster by adopting a first keyword extraction algorithm according to a group of words corresponding to the cluster.

In some embodiments of the present application, the processor is further configured to: determining a second keyword in a group of words corresponding to the cluster by adopting a second keyword extraction algorithm; determining subject terms corresponding to the clusters based on the second keywords and the first keywords corresponding to the clusters;

the treatment appliance is configured to: and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the subject term corresponding to the cluster.

In some embodiments of the present application, the processor is further configured to: acquiring a first query statement of a cluster center of each cluster;

the treatment appliance is configured to: and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency, the subject term corresponding to the cluster and the first query statement at the cluster center of the cluster.

and aiming at each cluster, taking the first query statement with the most times of cluster occurrence, the subject term corresponding to the cluster and the term with the most times of repetition in the first query statement at the cluster center of the cluster as the requirement name corresponding to the cluster.

obtaining current scores corresponding to all the required names from the user logs;

and determining whether each demand name is a new demand or not based on the current score corresponding to each demand name.

expanding the existing requirements according to the new requirements;

and for each new demand, optimizing the current semantic engine corresponding to the new demand type according to the type of the new demand, so that the semantic engine supports the business positioning of the new demand and the business processing of the new demand.

for each new demand, if the new demand is a new field, expanding the new field;

if the new demand is a new intention in the existing field, expanding the new intention in the existing field;

and if the new requirement is a new statement under the existing intention, expanding the new statement under the existing intention.

In some embodiments of the present application, the apparatus is applied in a server.

In some embodiments of the present application, the apparatus is applied to a display device, and the display device further includes:

a display for presenting the determined new demand.

In some embodiments of the present application, the display is further configured to present information related to each cluster.

A second aspect of the present application provides a method for processing a user log, including:

determining a new requirement based on the first query statement;

In some embodiments of the present application, the method further comprises:

the determining new requirements based on the first query statement comprises:

In some embodiments of the present application, determining the first query statements in the user log and determining the occurrence number corresponding to each first query statement includes:

acquiring a target query statement in a user log;

In some embodiments of the present application, the obtaining a target query statement in a user log includes:

In some embodiments of the present application, preprocessing the target query statement to obtain the first query statement and the occurrence number corresponding to each first query statement includes:

In some embodiments of the present application, clustering the first query statement to obtain the first query statement included in each cluster includes:

In some embodiments of the present application, the method further comprises:

determining a first keyword corresponding to each cluster according to a first query statement included in each cluster;

for each cluster, determining a requirement name corresponding to the cluster according to each first query statement in the cluster and the occurrence frequency corresponding to each first query statement, including:

and aiming at each cluster, determining a requirement name corresponding to the cluster according to the first query statement with the largest occurrence frequency of the cluster and the first keyword corresponding to the cluster.

In some embodiments of the application, determining, according to the first query statement included in each cluster, a first keyword corresponding to each cluster includes:

In some embodiments of the application, for each cluster, performing word segmentation on each first query statement included in the cluster, and performing screening processing according to a preset screening rule, after a group of words corresponding to the cluster is obtained, the method further includes:

determining a second keyword in a group of words corresponding to the cluster by adopting a second keyword extraction algorithm;

determining subject terms corresponding to the clusters based on the second keywords and the first keywords corresponding to the clusters;

the determining, for each cluster, a requirement name corresponding to the cluster according to the first query statement with the largest occurrence number of the cluster and the keyword corresponding to the cluster includes:

and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the subject term corresponding to the cluster.

In some embodiments of the present application, for each cluster, before determining a requirement name corresponding to the cluster according to the first query statement with the largest occurrence number of clusters and the subject term corresponding to the cluster, the method further includes:

acquiring a first query statement of a cluster center of each cluster;

for each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the subject term corresponding to the cluster, including:

and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency, the subject term corresponding to the cluster and the first query statement at the cluster center of the cluster.

In some embodiments of the present application, for each cluster, determining a requirement name corresponding to the cluster according to the first query statement with the largest occurrence number of the cluster, the subject term corresponding to the cluster, and the first query statement at the cluster center of the cluster, includes:

In some embodiments of the present application, determining a new requirement based on a requirement name corresponding to each cluster includes:

In some embodiments of the present application, optimizing a current semantic engine based on the new requirement, so that the semantic engine supports business positioning of the new requirement and business processing of the new requirement, includes:

expanding the existing requirements according to the new requirements;

In some embodiments of the present application, expanding existing requirements according to the new requirements includes:

for each new demand, if the new demand is a new field, expanding the new field;

A third aspect of the present application provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, perform a method as set forth in the second aspect above and in various possible designs of the second aspect.

According to the processing device and method for the user log, the new requirements are determined based on the abnormal query sentences in the user log, and the semantic engine is optimized based on the new requirements, so that the semantic engine can support the business positioning of the new requirements and can support the corresponding business processing of the new requirements, the business capability of the semantic engine is improved, the result is accurately fed back to the user, and the problems that the query sentences of the user cannot be analyzed or not supported by the semantic engine or the feedback result does not meet the user requirements and the like easily occur in the related technology, the user cannot be accurately provided with services, and the user experience is poor are solved.

Drawings

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

FIG. 1 is a schematic diagram of an architecture of a processing system according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a device for processing a user log according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of another user log processing apparatus according to an embodiment of the present application;

fig. 4 is an exemplary block diagram of a device for processing a user log according to an embodiment of the present application;

fig. 5 is a block diagram of a hardware configuration of a display device 200 according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating a process of determining a new requirement based on a first query statement according to an embodiment of the present application;

fig. 7 is a schematic flow chart of clustering according to an embodiment of the present application;

fig. 8 is a flowchart illustrating a process of determining a requirement name corresponding to a cluster according to an embodiment of the present application.

With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.

Detailed Description

To make the objects, embodiments and advantages of the present application clearer, the following description of exemplary embodiments of the present application will clearly and completely describe the exemplary embodiments of the present application with reference to the accompanying drawings in the exemplary embodiments of the present application, and it is to be understood that the described exemplary embodiments are only a part of the embodiments of the present application, and not all of the embodiments.

All other embodiments, which can be derived by a person skilled in the art from the exemplary embodiments described herein without inventive step, are intended to be within the scope of the claims appended hereto. In addition, while the disclosure herein has been presented in terms of one or more exemplary examples, it should be appreciated that aspects of the disclosure may be implemented solely as a complete embodiment.

It should be noted that the brief descriptions of the terms in the present application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of the present application. These terms should be understood in their ordinary and customary meaning unless otherwise indicated.

The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between similar or analogous objects or entities and are not necessarily intended to limit the order or sequence of any particular one, Unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein.

Furthermore, the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a product or device that comprises a list of elements is not necessarily limited to those elements explicitly listed, but may include other elements not expressly listed or inherent to such product or device.

The term "module," as used herein, refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and/or software code that is capable of performing the functionality associated with that element.

For clear understanding of the technical solutions of the present application, the solutions of the related art will be described in detail first. In the related technology, when a user controls an intelligent home through voice, the intelligent home recognizes the voice of the user, generates a corresponding query statement and sends the query statement to a server, but due to different user requirements, for example, different descriptions of the same thing, a semantic engine deployed by the server may not meet all the requirements of the user, and a situation that the query statement of the user cannot be analyzed or unsupported easily occurs, so that an accurate feedback result cannot be provided for the user, or although the query statement is analyzed by the semantic engine, the query statement does not have corresponding business support, so that an accurate feedback result cannot be provided for the user.

In view of the above problems in the related art, the inventors have conducted creative research and found that query statements that the semantic engine fails to resolve or support and query statements whose semantic engine feedback results do not meet the user requirements are recorded in the user log and may be referred to as abnormal query statements. The inventor creatively thinks that the abnormal query sentences in the user log can be deeply mined, so that a large number of new requirements can be mined, and the semantic engine is optimized based on the new requirements, so that the semantic engine supports the business positioning of the new requirements and has corresponding business support capability for the new requirements, and the results are accurately fed back to the user. Therefore, the embodiment of the application provides a method for processing a user log, and a semantic engine is optimized based on a new requirement mined by abnormal query statements in the user log, so that the accuracy of the semantic engine in responding to a user is improved.

Fig. 1 is a schematic diagram of an architecture of a processing system according to an embodiment of the present application. The processing system may include a server and at least one intelligent terminal. The intelligent terminal can be an intelligent household device, such as a display device, an intelligent television, an intelligent sound box and the like, and can also be any other user terminal, such as a mobile terminal, a tablet computer, a notebook computer and the like. In practical application, the intelligent terminal can convert user voice into a query sentence in a text format and send the query sentence to the server, or directly send the user voice to the server, and the server performs voice recognition to obtain the query sentence of the user. For example, the slot field records the query statement of the user, the feedback result field records the feedback result of the query statement of the user, and so on. The server can analyze abnormal query sentences based on user logs for mining new requirements, so that the semantic engine is optimized based on the new requirements, the semantic engine supports more service positioning of the new requirements and has service capacity for the new requirements, and service is provided for users more accurately.

In some embodiments, the specific operation of performing new requirement mining based on the abnormal query statement may be executed in the display device, the display device may obtain the user log from a server storing the user log, determine the new requirement based on the abnormal query statement in the user log, and optimize the current semantic engine of the display device based on the determined new requirement, so that the semantic engine supports service positioning of the new requirement and service processing of the new requirement, and the specific manner of executing the operation is the same as or similar to that described above, which is not described herein again.

In some embodiments, the display device is also in data communication with the server through a plurality of communication means, which may allow the intelligent terminal to be in communication connection through a Local Area Network (LAN), a Wireless Local Area Network (WLAN), and other networks. The server can provide various contents and interactions to the intelligent terminal. Illustratively, the intelligent terminal receives software program updates, or accesses a remotely stored digital media library, by sending and receiving information, as well as Electronic Program Guide (EPG) interactions.

The display device may be a liquid crystal display, an OLED display, a projection display device. The particular display device type, size, resolution, etc. are not limiting, and those skilled in the art will appreciate that the display device may be modified in performance and configuration as desired.

The display device may additionally provide an intelligent network tv function of a computer support function in addition to the broadcast receiving tv function, including but not limited to, a network tv, an intelligent tv, an Internet Protocol Tv (IPTV), and the like.

In some embodiments, a server may be one server, one server cluster, or multiple server clusters, and may include one or more types of servers. For example, the user log is stored in a first server in the server cluster, the second server responds to the user service request, and the third server processes the user log.

In some embodiments, the newly generated user logs can be mined and optimized in a timing manner, the service capability of the semantic engine is continuously improved, and the problems that the query statement of the user cannot be analyzed or not supported by the semantic engine or the feedback result does not meet the user requirement and the like easily occur in the related technology, so that the service cannot be accurately provided for the user and the user experience is poor are solved.

The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.

An embodiment of the present application provides a processing apparatus for a user log, which is used for processing the user log.

As shown in fig. 2, a schematic structural diagram of a device for processing a user log according to this embodiment is provided. The processing device of the user log comprises: a processor 11.

The processor 11 is configured to:

acquiring a user log, and determining a first query statement in the user log, wherein the first query statement is a query statement which is determined to be abnormal through the whole life cycle of the user query statement analyzed by a semantic engine, and/or a query statement with an abnormal result fed back by the semantic engine; determining a new requirement based on the first query statement; and optimizing the current semantic engine based on the new requirement so that the semantic engine supports the business positioning of the new requirement and the business processing of the new requirement.

The processing device of the user log can be applied to the server or the display device. The user log may be obtained from a storage area where the user log is stored. In some embodiments, the server may be a distributed server cluster. Such as a user log, is stored on a first server in the server cluster and a second server in the server cluster is responding to the user service request. The processing means of the user log obtains the user log from a first server storing the user log.

After the user log is obtained, a first query statement in the user log can be determined, wherein the first query statement is a query statement which is determined to be abnormal through the whole life cycle of the user query statement analyzed by the semantic engine, and/or a query statement with an abnormal result fed back by the semantic engine.

In some embodiments, the user log may be parsed to extract abnormal query statements therein, and in order to distinguish what may be referred to as target query statements, for example, a query statement (which may be referred to as a second query statement) that cannot be parsed or is not supported by a semantic engine in the user log may be obtained through a field, an intention, and a vertical domain parsing slot field as a target query statement; for example, a query statement (which may be referred to as a third query statement) in the user log, for which the feedback result does not meet the user requirement, may be obtained as the target query statement through the final feedback result field of the semantic engine. The second query statement and the third query statement may also be obtained as target query statements, which may be specifically set according to actual requirements.

After the target query statement is obtained, the target query statement often has repeated query statements, and the target query statement needs to be deduplicated to obtain a non-repeated query statement as a first query statement.

In some embodiments, before the target query statement is deduplicated, statistics on repeated query statements in the target query statement are further required to determine the occurrence number of the same query statement.

Illustratively, the target query statement includes 10 query statements, of which there are 3 query statements a, 4 query statements B and 3 query statements C, and then 3 query statements remain after deduplication: query statement A, query statement B, and query statement C. That is, 3 first query statements are obtained after deduplication, wherein the occurrence frequency corresponding to the query statement a is 3, the occurrence frequency corresponding to the query statement B is 4, and the occurrence frequency corresponding to the query statement C is 3.

After the first query statement is obtained, a new requirement may then be determined based on the first query statement.

In some embodiments, the new requirement may be determined based on the clustering result by clustering the first query statement.

In some embodiments, the new requirement may also be determined based on the clustering results in combination with the number of occurrences of each first query statement.

In some embodiments, the new requirements may also be determined based on the clustering results in conjunction with keyword extraction for each cluster.

After the new requirements are mined, the current semantic engine can be optimized based on the new requirements, so that the semantic engine supports the business positioning of the new requirements and the business processing of the new requirements.

For example, if the new requirement is a new expression "forecast of city B" under the existing intention a, and the existing expression is a weather forecast of city B, the new expression may be added to the expression under the existing intention a, and the semantic engine is optimized based on the new expression, so that when the semantic engine parses the new expression again, the requirement of the user can be understood, and the result can be accurately fed back to the user. For example, if the query sentence of the user is that i wants to know the forecast of the city B, the semantic engine can understand that the user needs to know the forecast of the city B, and can search the forecast of the city B and feed the forecast back to the user for listening.

In some embodiments, the semantic engine may be optimized according to a specific type of a new requirement, for example, the new requirement is a new domain, and an existing domain of the semantic engine does not support the new requirement, so that business support for the semantic engine for a related statement of the new domain needs to be added, and business support for different intentions under the new domain can also be added. For example, if the new requirement is only a new idea in the existing field, the semantic engine needs to be added with business support for the new idea-related grammar. For example, if the new domain is only a new grammar (i.e. a new grammar under the existing intention of the existing domain), and the existing service of the current semantic engine does not support the new grammar, the service support for the new grammar needs to be added to the semantic engine, and so on. The specific optimization mode may be set according to actual requirements, and this embodiment is not limited.

Fig. 3 is a schematic structural diagram of another user log processing apparatus provided in this embodiment.

In some embodiments, the processing means of the user log may further comprise a memory 12. The memory 12 stores computer-executable instructions, and the processor 11 reads the computer-executable instructions stored in the memory to perform corresponding operations in the embodiments of the present application.

According to the processing device for the user log, the new requirements are determined based on the abnormal query statements in the user log, and the semantic engine is optimized based on the new requirements, so that the semantic engine can support the service positioning of the new requirements and can support the corresponding service processing of the new requirements, the service capability of the semantic engine is improved, the result is accurately fed back to the user, and the problems that the query statements of the user cannot be analyzed or not supported by the semantic engine, or the feedback result does not meet the user requirements and the like easily occur in the related technology, the service cannot be accurately provided for the user, and the user experience is poor are caused are solved.

In some embodiments, the processor is further configured to: determining the occurrence frequency corresponding to each first query statement; accordingly, the treatment appliance is configured to: clustering the first query sentences to obtain first query sentences included in each cluster; aiming at each cluster, determining a requirement name corresponding to the cluster according to each first query statement in the cluster and the occurrence frequency corresponding to each first query statement; and determining new requirements based on the requirement names corresponding to the clusters.

The occurrence frequency corresponding to each first query statement may be obtained by counting repeated query statements in the target query statement before the target query statement is deduplicated. For example, the target query statement includes 10 query statements, where there are 3 query statements a, 4 query statements B, and 3 query statements C, and then 3 query statements remain after deduplication: query statement A, query statement B, and query statement C. That is, 3 first query statements are obtained after deduplication, wherein the occurrence frequency corresponding to the query statement a is 3, the occurrence frequency corresponding to the query statement B is 4, and the occurrence frequency corresponding to the query statement C is 3.

After the first query statement is obtained, the first query statement may be clustered by using a preset clustering algorithm to obtain at least one cluster, and the first query statement included in each cluster may be obtained.

The preset clustering algorithm can adopt any practicable clustering algorithm, such as Mean Shift algorithm, K-Means algorithm and the like, and can be specifically set according to actual requirements.

After clustering, for each cluster, determining a requirement name corresponding to the cluster according to each first query statement included in the cluster and the occurrence number corresponding to each first query statement.

In some embodiments, the first query statements may be ranked based on the occurrence frequency corresponding to each first query statement to obtain the first query statement with the highest occurrence frequency, and the first query statement with the highest occurrence frequency is used as the requirement name corresponding to the cluster, or a keyword is extracted from the first query statement with the highest occurrence frequency and used as the requirement name corresponding to the cluster.

In some embodiments, a preset number of first query sentences with the highest occurrence frequency ranking may also be obtained, and the first query sentences are subjected to word segmentation and screening to extract keywords, so as to determine the demand name corresponding to the cluster. The method can be specifically set according to actual requirements.

In some embodiments, the number of occurrences of each first query statement may be combined with other factors to determine the requirement name of the cluster. For example, one or more keywords corresponding to the cluster are extracted based on each first query statement in the cluster, and the requirement name corresponding to the cluster is determined by combining the first query statement with the largest occurrence number in the cluster and the one or more keywords corresponding to the cluster. The requirement name of the cluster may also be determined in conjunction with the first query statement at the cluster center. The method can be specifically set according to actual requirements.

After the requirement name corresponding to each cluster is obtained, a new requirement may be mined based on the requirement name of each cluster, for example, the requirement name may be matched with an existing requirement based on the requirement name, and whether the requirement name is a new requirement is determined according to a matching result.

For each new requirement, the new requirement may correspond to a new domain, a new intent, or a new law.

Alternatively, it is also possible to combine manual work to determine new requirements.

After the new requirement is determined, the current semantic engine can be optimized based on the new requirement, so that the semantic engine supports the business positioning of the new requirement and can accurately perform corresponding business processing on the new requirement.

The processing apparatus for a user log provided in this embodiment clusters abnormal query statements in the user log, determines a requirement name corresponding to the cluster based on the query statements in each cluster obtained by the clustering and corresponding occurrence times, determines a new requirement based on the requirement name of each cluster, and optimizes a semantic engine based on the new requirement, so that the semantic engine can support service location of the new requirement and perform corresponding service processing on the new requirement, thereby improving service capability of the semantic engine, accurately feeding back a result for a user, and solving the problem that the query statements of the user are not resolved or supported by the semantic engine easily or a feedback result does not meet the user requirement and the like in the related art, thereby not accurately providing a service for the user, and resulting in poor user experience.

In some embodiments, the treatment appliance is configured to:

acquiring a target query statement in a user log; and preprocessing the target query statement to obtain the first query statement and the occurrence frequency corresponding to each first query statement, wherein the first query statements are not repeated.

Specifically, the user log may be analyzed to extract an abnormal query statement therein, which is used as a target query statement, for example, a query statement (which may be referred to as a second query statement) that cannot be analyzed or is not supported by a semantic engine in the user log may be obtained through a field, an intention, and a vertical field analysis slot field as a target query statement; for example, a query statement (which may be referred to as a third query statement) in the user log, for which the feedback result does not meet the user requirement, may be obtained as the target query statement through the final feedback result field of the semantic engine. The second query statement and the third query statement may also be obtained as target query statements, which may be specifically set according to actual requirements.

After the target query statement is obtained, the target query statement may be preprocessed to obtain the first query statement and the occurrence frequency corresponding to each first query statement. The preprocessing specifically includes counting the number of occurrences of the same query statement and deduplication processing. The finally obtained first query statements are not repeated with each other.

In some embodiments, the treatment appliance is configured to:

extracting a second query statement which cannot be analyzed or not supported by the semantic engine and/or a third query statement of which the semantic engine feedback result does not meet the user requirement from the user log according to a preset extraction rule; the second query statement and/or the third query statement are/is taken as the target query statement.

Specifically, query statements which cannot be analyzed or are not supported by a semantic engine in a user log can be obtained through the fields, intentions and vertical domain analysis slot fields and serve as second query statements; and obtaining the query statement of which the feedback result does not meet the requirement of the user in the user log as a third query statement through a final feedback result field of the semantic engine. For example, the feedback result is "no answer, i do not understand your words".

In some embodiments, the treatment appliance is configured to:

counting the target query sentences to obtain the same occurrence times of the target query sentences; and carrying out duplication removal on the target query statement to obtain a nonrepeated target query statement as a first query statement.

In some embodiments, the treatment appliance is configured to:

generating sentence vectors corresponding to the first query sentences according to a preset generation rule; and clustering the first query sentences based on a preset clustering algorithm and sentence vectors corresponding to the first query sentences to obtain the first query sentences included in each cluster.

In some embodiments, the preset generation rule may be a BERT model, specifically, the BERT-as-service model may be used, or other implementable manners, which is not limited in this embodiment. BERT-as-service is an open source BERT service that allows users to use BERT models in a manner that calls services without concern for BERT implementation details. The bert-as-service is divided into a client and a server, and a user can call services from python codes and can also access the services in an http mode.

After the sentence vectors corresponding to the first query sentences are generated, clustering the first query sentences based on a preset clustering algorithm and the sentence vectors corresponding to the first query sentences to obtain the first query sentences included in each cluster. Specifically, the first query statement is clustered based on the distance of each sentence vector in space.

In some embodiments, the predetermined clustering algorithm may be any practicable clustering algorithm in the related art, such as a Mean Shift algorithm, a K-Means algorithm, and the like.

In some embodiments, the processor is further configured to: determining a first keyword corresponding to each cluster according to a first query statement included in each cluster;

the treatment device body is configured to: and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the first keyword corresponding to the cluster.

Specifically, the requirement name corresponding to each cluster may be determined by combining two factors, i.e., the first query statement appearing most frequently in the cluster and the keyword extracted for the cluster (referred to as the first keyword for distinction). The first keyword may be one or more. Specifically, the first query statement with the largest occurrence number and the word with the largest repetition number in the first keyword may be used as the requirement name corresponding to the cluster. For example, the first query statement with the largest occurrence number is "i want to see three movies", and the keyword extracted for the cluster includes "movie", then the requirement name corresponding to the cluster may be "movie".

In some embodiments, the treatment appliance is configured to:

for each cluster, performing word segmentation on each first query statement included in the cluster, and performing screening processing according to a preset screening rule to obtain a group of words corresponding to the cluster; and extracting a first keyword corresponding to the cluster by adopting a first keyword extraction algorithm according to a group of words corresponding to the cluster.

In some embodiments, the word segmentation may employ any practicable word segmentation algorithm, such as jieba (jieba) word segmentation, where a part of speech of each word is obtained when the word segmentation is performed, a filtering rule may be preset, and a result obtained by the word segmentation is filtered, where the filtering rule may include a part of speech filtering rule, a stop word filtering rule, a semantization removing rule, and the like, the part of speech filtering may be, for example, to filter out adjectives, adverbs, specific nouns, and the stop word filtering may be based on a general stop word bank, an exclusive stop word bank in different fields, and a custom stop word. Such as "o", "j", "kah", etc. The semantization can be based on the existing label system, some words are replaced by corresponding labels, such as a certain cartoon A, if the label is a cartoon, the word can be replaced by the cartoon, and the specific screening rule can be set according to the actual requirement.

In some embodiments, the first keyword extraction algorithm may be a TF-IDF algorithm, TF-IDF (Term Frequency-Inverse Document Frequency) being a weighting technique for information retrieval and data mining. TF means Term Frequency (Term Frequency), and IDF means Inverse text Frequency index (Inverse Document Frequency). TF represents the frequency of occurrence of a word in an article, and in the application, the frequency of occurrence of a word in all words obtained by word segmentation results is represented.

Illustratively, a group of words corresponding to a cluster includes a total number of words of 100, wherein, if a word a appears as 5 words, the word frequency TF of the word a is determined_AThe number of times the word a appears/total word number is 5/100.

IDF of word A_ALog (total number of samples/(number of samples containing the word +1)), in the present application, the total number of samples may refer to the number of clusters, and the number of samples containing the word refers to the number of clusters containing the word. The TF-IDF algorithm may be used to evaluate the importance of a word to one of a set of documents or a corpus. The importance of a word increases in proportion to the number of times it appears in a document, but at the same time decreases in inverse proportion to the frequency with which it appears in the corpus. In this application, if the frequency TF of a word occurring in its cluster is high, and rarely occurs in other clustersIf the word appears, the word is considered to have good category distinguishing capability.

The first keyword extracted by the first keyword extraction algorithm may be a keyword with a weight greater than a first weight threshold value, which is selected as the first keyword according to the obtained weight of each keyword and the first weight threshold value.

In some embodiments, the processor is further configured to: determining a second keyword in a group of words corresponding to the cluster by adopting a second keyword extraction algorithm; determining subject terms corresponding to the clusters based on the second keywords and the first keywords corresponding to the clusters; the treatment device body is configured to: and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the subject term corresponding to the cluster.

Specifically, for each cluster, a second keyword extraction algorithm may be further used to determine a second keyword in a group of words corresponding to the cluster, and the subject word corresponding to the cluster is determined by combining the first keyword and the second keyword. And taking repeated keywords in the first keywords and the second keywords as subject words corresponding to the cluster. Therefore, the first query statement with the largest occurrence number and the subject term can be combined to determine the cluster requirement name, and the accuracy of the determined requirement name is improved.

In some embodiments, the second keyword extraction algorithm may be a TextRank algorithm, or any other algorithm that can obtain a weight. The TextRank algorithm is an algorithm which can be separated from the background of a corpus and can extract keywords of a document only by analyzing a single document. The specific principle is the prior art, and is not described herein again.

In some embodiments, the processor is further configured to: acquiring a first query statement of a cluster center of each cluster;

the treatment device body is configured to: and aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency, the subject term corresponding to the cluster and the first query statement at the cluster center of the cluster.

Specifically, for each cluster, the first query statement at the cluster center, the first query statement with the largest occurrence frequency and the subject term corresponding to the cluster can be combined to determine the demand name corresponding to the cluster, so that the accuracy of the determined demand name is further improved.

The first query sentences at the cluster center may be obtained during clustering, that is, the first query sentences may be determined based on a distance between a sentence vector corresponding to each first query sentence and the cluster center. The distance may be a euclidean distance or other means for representing the distance between sentence vectors, and may be specifically set according to the requirements of an actual clustering algorithm.

In some embodiments, the treatment appliance is configured to:

and aiming at each cluster, taking the first query statement with the most times of occurrence of the cluster, the subject term corresponding to the cluster and the term with the most times of repetition in the first query statement at the cluster center of the cluster as the requirement name corresponding to the cluster.

For example, the first query statement that appears most frequently in a cluster is "how tomorrow weather appears", the first query statement at the center of the cluster is "i want to know tomorrow weather", and the subject words corresponding to the cluster are "weather" and "tomorrow". Then it may be determined that "weather" is the name of the demand corresponding to the cluster.

In some embodiments, the treatment appliance is configured to:

acquiring current scores corresponding to the demand names from a user log; and determining whether each demand name is a new demand or not based on the current score corresponding to each demand name.

Specifically, the semantic engine scores query sentences in the service positioning process, that is, the probability of a certain intention currently belonging to a certain field, and after determining a requirement name corresponding to each cluster, the semantic engine may determine a current score corresponding to the requirement name based on a current score corresponding to a first query sentence to which the requirement name relates. If the current score of the demand name is lower than the threshold, the current business location of the demand can be considered as wrong, and the demand is determined to be a new demand.

In some embodiments, after determining each new requirement, each new requirement may be further output to a terminal of a corresponding responsible person, and displayed to the responsible person, so that the responsible person further confirms whether the new requirement is indeed the new requirement. If the requirement is a new requirement, the responsible personnel can optimize the current semantic engine by themselves or inform other related personnel of the new requirement.

In some embodiments, the treatment appliance is configured to:

expanding the existing requirements according to the new requirements; and for each new demand, optimizing the current semantic engine corresponding to the new demand type according to the new demand type, so that the semantic engine supports the business positioning of the new demand and the business processing of the new demand.

In some embodiments, the treatment appliance is configured to:

for each new demand, if the new demand is a new field, expanding the new field; if the new demand is a new intention in the existing field, expanding the new intention in the existing field; if the new requirement is a new expression under the existing intention, the new expression is expanded under the existing intention.

Specifically, the semantic engine may be optimized according to a specific type of a new requirement, for example, the new requirement is a new field, and an existing field of the semantic engine does not support the new requirement, so that the new field needs to be expanded, and business support for the new field needs to be added to the semantic engine. For example, if the new requirement is only a new idea of an existing domain, the new idea needs to be expanded in the existing domain, and a semantic engine is added with service support related to the new idea. For example, the new domain is only a new utterance under the existing intention, and only the existing business of the current semantic engine is not supported, the new utterance needs to be extended for the existing intention, and business support for the new utterance needs to be added to the semantic engine.

In some embodiments, the processing means of the user log is applied in a server.

In some embodiments, the processing means of the user log is applied in a display device, which may further comprise a display, which may be used to present the determined new requirements.

In some embodiments, the display may also be used to present information about each cluster, such as cluster identification, cluster name, cluster size, query statements ranked in number of occurrences within a cluster and the number of queries thereof, and so on.

In an exemplary embodiment, as shown in fig. 4, which is an exemplary block diagram of a processing apparatus of a user log provided in this embodiment, the processing apparatus 20 of the user log may be applied to a server, and may also be applied to a display device.

The processing means 20 of the user log may comprise one or more of the following components: processing components 21, memory 22, power components 23, communication components 24, and so on.

The processing component 21 generally controls the overall operation of the processing means 20 of the user log. The processing components 21 may include one or more processors 25 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 21 may include one or more modules that facilitate interaction between the processing component 21 and other components.

The memory 22 is configured to store various types of data to support the operation of the processing device 20 at the user log. Examples of such data include instructions for any application or method operating on the processing device 20 of the user log. The memory 22 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 23 provides power to the various components of the processing means 20 for user logs. The power components 23 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the processing device 20 of the user log.

The communication component 24 is configured to facilitate wired or wireless communication between the processing means 20 of the user log and other devices.

In an exemplary embodiment, the processing means 20 of the user log may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as the memory 22 comprising instructions, executable by the processor 25 of the processing device 20 of the user log to perform the above method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

As shown in fig. 5, a block diagram of a hardware configuration of the display device 200 provided for the present embodiment is provided.

In some embodiments, at least one of the controller 250, the tuner demodulator 210, the communicator 220, the detector 230, the input/output interface 255, the display 275, the audio output interface 285, the memory 260, the power supply 290, the user interface 265, and the external device interface 240 is included in the display apparatus 200.

In some embodiments, a display 275 receives image signals originating from the first processor output and displays video content and images and components of the menu manipulation interface.

In some embodiments, the display 275, includes a display screen assembly for presenting a picture, and a driving assembly that drives the display of an image.

In some embodiments, the video content is displayed from broadcast television content, or alternatively, from various broadcast signals that may be received via wired or wireless communication protocols. Alternatively, various image contents received from the network communication protocol and sent from the network server side can be displayed.

In some embodiments, the display 275 is used to present a user-manipulated UI interface generated in the display apparatus 200 and used to control the display apparatus 200.

In some embodiments, a driver assembly for driving the display is also included, depending on the type of display 275.

In some embodiments, display 275 is a projection display and may also include a projection device and a projection screen.

In some embodiments, communicator 220 is a component for communicating with external devices or external servers according to various communication protocol types. For example: the communicator may include at least one of a Wifi chip, a bluetooth communication protocol chip, a wired ethernet communication protocol chip, and other network communication protocol chips or near field communication protocol chips, and an infrared receiver.

In some embodiments, the display apparatus 200 may establish control signal and data signal transmission and reception with the external control apparatus 1001 or the content providing apparatus through the communicator 220.

In some embodiments, the user interface 265 may be configured to receive infrared control signals from a control device 1001 (e.g., an infrared remote control, etc.).

In some embodiments, the detector 230 is a signal used by the display device 200 to collect an external environment or interact with the outside.

In some embodiments, the detector 230 includes a light receiver, a sensor for collecting the intensity of ambient light, and parameters changes can be adaptively displayed by collecting the ambient light, and the like.

In some embodiments, an image collector 232 in the detector 230, such as a camera, a video camera, etc., may be used to collect external environment scenes, collect attributes of a user or gestures interacted with the user, adaptively change display parameters, and also recognize user gestures, so as to implement a function of interaction with the user.

In some embodiments, the detector 230 may also include a temperature sensor or the like, such as by sensing ambient temperature.

In some embodiments, the display apparatus 200 may adaptively adjust a display color temperature of an image. For example, the display apparatus 200 may be adjusted to display a cool tone when the temperature is in a high environment, or the display apparatus 200 may be adjusted to display a warm tone when the temperature is in a low environment.

In some embodiments, the detector 230 may further include a sound collector 231, such as a microphone, for collecting voice data, wherein when the user speaks an instruction by voice, the microphone can collect voice data including the instruction spoken by the user. For example, the sound collector 231 may collect a voice signal including a control instruction of the user to control the display device 200, or collect an ambient sound for recognizing an ambient scene type, so that the display device 200 may adaptively adapt to an ambient noise.

In some embodiments, as shown in fig. 5, the input/output interface 255 is configured to allow data transfer between the controller 250 and external other devices or other controllers 250. Such as receiving video signal data and audio signal data of an external device, or command instruction data, etc.

In some embodiments, the external device interface 240 may include, but is not limited to, the following: the interface can be any one or more of a high-definition multimedia interface (HDMI), an analog or data high-definition component input interface, a composite video input interface, a USB input interface, an RGB port and the like. The plurality of interfaces may form a composite input/output interface.

In some embodiments, as shown in fig. 5, the tuning demodulator 210 is configured to receive a broadcast television signal through a wired or wireless receiving manner, perform modulation and demodulation processing such as amplification, mixing, resonance, and the like, and demodulate an audio and video signal from a plurality of wireless or wired broadcast television signals, where the audio and video signal may include a television audio and video signal carried in a television channel frequency selected by a user and an EPG data signal.

In some embodiments, the frequency points demodulated by the tuner demodulator 210 are controlled by the controller 250, and the controller 250 can send out control signals according to user selection, so that the modem responds to the television signal frequency selected by the user and modulates and demodulates the television signal carried by the frequency.

In some embodiments, the broadcast television signal may be classified into a terrestrial broadcast signal, a cable broadcast signal, a satellite broadcast signal, an internet broadcast signal, or the like according to the broadcasting system of the television signal. Or may be classified into a digital modulation signal, an analog modulation signal, and the like according to a modulation type. Or the signals are classified into digital signals, analog signals and the like according to the types of the signals.

In some embodiments, the controller 250 and the modem 210 may be located in different separate devices, that is, the modem 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box. Therefore, the set top box outputs the television audio and video signals modulated and demodulated by the received broadcast television signals to the main body equipment, and the main body equipment receives the audio and video signals through the first input/output interface.

In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 may control the overall operation of the display apparatus 200. For example: in response to receiving a user command for selecting a UI object to be displayed on the display 275, the controller 250 may perform an operation related to the object selected by the user command.

In some embodiments, the object may be any one of selectable objects, such as a hyperlink or an icon. Operations related to the selected object, such as: displaying an operation connected to a hyperlink page, document, image, or the like, or performing an operation of a program corresponding to the icon. The user command for selecting the UI object may be a command input through various input means (e.g., a mouse, a keyboard, a touch pad, etc.) connected to the display apparatus 200 or a voice command corresponding to a voice spoken by the user.

As shown in fig. 5, the controller 250 includes at least one of a Random Access Memory 251 (RAM), a Read-Only Memory 252 (ROM), a video processor 270, an audio processor 280, other processors 253 (e.g., a Graphics Processing Unit (GPU), a Central Processing Unit 254 (CPU), a Communication Interface (Communication Interface), and a Communication Bus 256(Bus), which connects the respective components.

In some embodiments, RAM 251 is used to store temporary data for the operating system or other programs that are running

In some embodiments, ROM 252 is used to store instructions for various system boots.

In some embodiments, the ROM 252 is used to store a Basic Input Output System (BIOS). The system is used for completing power-on self-test of the system, initialization of each functional module in the system, a driver of basic input/output of the system and booting an operating system.

In some embodiments, when the power-on signal is received, the display device 200 starts to power up, the CPU executes the system boot instruction in the ROM 252, and copies the temporary data of the operating system stored in the memory to the RAM 251 so as to start or run the operating system. After the start of the operating system is completed, the CPU copies the temporary data of the various application programs in the memory to the RAM 251, and then, the various application programs are started or run.

In some embodiments, CPU processor 254 is used to execute operating system and application program instructions stored in memory. And executing various application programs, data and contents according to various interactive instructions received from the outside so as to finally display and play various audio and video contents.

In some example embodiments, the CPU processor 254 may comprise a plurality of processors. The plurality of processors may include a main processor and one or more sub-processors. A main processor for performing some operations of the display apparatus 200 in a pre-power-up mode and/or operations of displaying a screen in a normal mode. One or more sub-processors for one operation in a standby mode or the like.

In some embodiments, the graphics processor 253 is used to generate various graphics objects, such as: icons, operation menus, user input instruction display graphics, and the like. The display device comprises an arithmetic unit which carries out operation by receiving various interactive instructions input by a user and displays various objects according to display attributes. And the system comprises a renderer for rendering various objects obtained based on the arithmetic unit, wherein the rendered objects are used for being displayed on a display.

In some embodiments, the video processor 270 is configured to receive an external video signal, and perform video processing such as decompression, decoding, scaling, noise reduction, frame rate conversion, resolution conversion, image synthesis, and the like according to a standard codec protocol of the input signal, so as to obtain a signal that can be displayed or played on the direct display device 200.

In some embodiments, video processor 270 includes a demultiplexing module, a video decoding module, an image synthesis module, a frame rate conversion module, a display formatting module, and the like.

The demultiplexing module is used for demultiplexing the input audio and video data stream, and if the input MPEG-2 is input, the demultiplexing module demultiplexes the input audio and video data stream into a video signal and an audio signal.

And the video decoding module is used for processing the video signal after demultiplexing, including decoding, scaling and the like.

And the image synthesis module is used for carrying out superposition mixing processing on the GUI signal input by the user or generated by the user and the video image after the zooming processing by the graphic generator so as to generate an image signal for display.

The frame rate conversion module is configured to convert an input video frame rate, such as a 60Hz frame rate into a 120Hz frame rate or a 240Hz frame rate, and the normal format is implemented in, for example, an interpolation frame mode.

The display format module is used for converting the received video output signal after the frame rate conversion, and changing the signal to conform to the signal of the display format, such as outputting an RGB data signal.

In some embodiments, the graphics processor 253 and the video processor may be integrated or separately configured, and when the graphics processor and the video processor are integrated, the graphics processor and the video processor may perform processing of graphics signals output to the display, and when the graphics processor and the video processor are separately configured, the graphics processor and the video processor may perform different functions, respectively, for example, a GPU + frc (frame Rate conversion) architecture.

In some embodiments, the audio processor 280 is configured to receive an external audio signal, decompress and decode the received audio signal according to a standard codec protocol of the input signal, and perform noise reduction, digital-to-analog conversion, and amplification processes to obtain an audio signal that can be played in a speaker.

In some embodiments, video processor 270 may comprise one or more chips. The audio processor may also comprise one or more chips.

In some embodiments, the video processor 270 and the audio processor 280 may be separate chips or may be integrated together with the controller in one or more chips.

In some embodiments, the audio output, under the control of controller 250, receives sound signals output by audio processor 280, such as: the speaker 286, and an external sound output terminal of a generating device that can output to an external device, in addition to the speaker carried by the display device 200 itself, such as: external sound interface or earphone interface, etc., and may also include a near field communication module in the communication interface, for example: and the Bluetooth module is used for outputting sound of the Bluetooth loudspeaker.

The power supply 290 supplies power to the display device 200 from the power input from the external power source under the control of the controller 250. The power supply 290 may include a built-in power supply circuit installed inside the display apparatus 200, or may be a power supply interface installed outside the display apparatus 200 to provide an external power supply in the display apparatus 200.

A user interface 265 for receiving an input signal of a user and then transmitting the received user input signal to the controller 250. The user input signal may be a remote controller signal received through an infrared receiver, and various user control signals may be received through the network communication module.

In some embodiments, a user inputs a user command through the control device 1001 or the mobile terminal, the user input interface is according to the user input, and the display apparatus 200 responds to the user input through the controller 250.

In some embodiments, a user may enter user commands on a Graphical User Interface (GUI) displayed on the display 275, and the user input interface receives the user input commands through the Graphical User Interface (GUI). Alternatively, the user may input the user command by inputting a specific sound or gesture, and the user input interface receives the user input command by recognizing the sound or gesture through the sensor.

In some embodiments, a "user interface" is a media interface for interaction and information exchange between an application or operating system and a user that enables conversion between an internal form of information and a form that is acceptable to the user. A commonly used presentation form of the User Interface is a Graphical User Interface (GUI), which refers to a User Interface related to computer operations and displayed in a graphical manner. It may be an interface element such as an icon, a window, a control, etc. displayed in the display screen of the electronic device, where the control may include a visual interface element such as an icon, a button, a menu, a tab, a text box, a dialog box, a status bar, a navigation bar, a Widget, etc.

The memory 260 includes a memory storing various software modules for driving the display device 200. Such as: various software modules stored in the first memory, including: at least one of a basic module, a detection module, a communication module, a display control module, a browser module, and various service modules.

The base module is a bottom layer software module for signal communication between various hardware in the display device 200 and for sending processing and control signals to the upper layer module. The detection module is used for collecting various information from various sensors or user input interfaces, and the management module is used for performing digital-to-analog conversion and analysis management.

For example, the voice recognition module comprises a voice analysis module and a voice instruction database module. The display control module is used for controlling the display to display the image content, and can be used for playing the multimedia image content, UI interface and other information. And the communication module is used for carrying out control and data communication with external equipment. And the browser module is used for executing a module for data communication between browsing servers. And the service module is used for providing various services and modules including various application programs. Meanwhile, the memory 260 may store a visual effect map for receiving external data and user data, images of various items in various user interfaces, and a focus object, etc.

It should be noted that the above embodiments may be implemented individually or in combination in any combination without conflict, and the present application is not limited thereto.

Another embodiment of the present application provides a method for processing a user log, which is used for processing the user log. The execution subject of this embodiment is a processing apparatus of the user log, and the processing apparatus of the user log may be provided in the server or the display device. The method specifically comprises the following steps:

It should be noted that, the method provided in the embodiment of the present application can implement all the operations implemented by the embodiment of the apparatus and achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the embodiment of the apparatus are omitted here.

In an exemplary embodiment, as shown in fig. 6, a schematic flow chart of determining a new requirement based on a first query statement is provided for this embodiment.

After the user log is obtained, the method further comprises the step of determining the occurrence frequency corresponding to each first query statement.

Correspondingly, determining a new requirement based on the first query statement may specifically include:

step 101, clustering the first query statement to obtain the first query statement included in each cluster.

And 102, aiming at each cluster, determining a requirement name corresponding to the cluster according to each first query statement in the cluster and the occurrence frequency corresponding to each first query statement.

Step 103, determining new requirements based on the requirement names corresponding to the clusters.

In an exemplary embodiment, determining the first query statement and the occurrence number in the user log specifically includes:

acquiring a target query statement in a user log; and preprocessing the target query statement to obtain the first query statement and the occurrence frequency corresponding to each first query statement.

Wherein the first query statements are not repeated.

In some embodiments, obtaining the target query statement in the user log comprises:

In some embodiments, preprocessing the target query statement to obtain the first query statement and the occurrence number corresponding to each first query statement includes:

In some embodiments, stop word removal processing may also be performed on the target query statement to remove stop words, such as "o", "e", and other stop words, from the target query statement.

In some embodiments, as shown in fig. 7, a schematic flow chart of clustering provided in this embodiment is provided. Namely, clustering the first query statement to obtain the first query statement included in each cluster, specifically including:

step 1011, generating sentence vectors corresponding to the first query sentences according to preset generation rules.

Step 1012, clustering the first query sentences based on a preset clustering algorithm and sentence vectors corresponding to the first query sentences to obtain the first query sentences included in each cluster.

In an exemplary embodiment, as shown in fig. 8, a flowchart for determining a requirement name corresponding to a cluster is provided for this embodiment. That is, after obtaining the first query statement included in the plurality of clusters, the method further includes:

step 2011, according to the first query statement included in each cluster, determining a first keyword corresponding to each cluster.

Correspondingly, for each cluster, determining a requirement name corresponding to the cluster according to each first query statement in the cluster and the occurrence frequency corresponding to each first query statement, including:

step 1021, aiming at each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the first keyword corresponding to the cluster.

In some embodiments, determining the first keyword corresponding to each cluster according to the first query statement included in each cluster includes:

In some embodiments, for each cluster, performing word segmentation on each first query statement included in the cluster, and performing screening processing according to a preset screening rule, to obtain a group of words corresponding to the cluster, the method further includes:

determining a second keyword in a group of words corresponding to the cluster by adopting a second keyword extraction algorithm; and determining the subject term corresponding to the cluster based on each second keyword and the first keyword corresponding to the cluster.

Correspondingly, for each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the keyword corresponding to the cluster, including:

In some embodiments, before determining, for each cluster, a requirement name corresponding to the cluster according to the first query statement with the largest number of occurrences of the cluster and the subject term corresponding to the cluster, the method further includes: and acquiring a first query statement of a cluster center of each cluster.

Correspondingly, for each cluster, determining a demand name corresponding to the cluster according to the first query statement with the largest cluster occurrence frequency and the subject term corresponding to the cluster, including:

In some embodiments, for each cluster, determining a requirement name corresponding to the cluster according to the first query statement with the largest cluster occurrence number, the subject term corresponding to the cluster, and the first query statement at the cluster center of the cluster, includes:

In some embodiments, determining the new demand based on the demand name corresponding to each cluster includes:

In some embodiments, optimizing the current semantic engine based on the new requirements such that the semantic engine supports business location of the new requirements and business processing of the new requirements includes:

In some embodiments, the existing requirements are augmented according to the new requirements, including:

In some embodiments, the clustering result may also be output, such as outputting each first query statement in the cluster and the corresponding occurrence number.

Illustratively, the output results of the clustering are as follows:

cluster _ top _ texts [ (' idiom ',210), (' idiom ',14), (' idiom maotai ',11), (' quadword ',10), (' idiom ',7), (' my intention to hear idiom ',7), (' saying idiom ',6), (' quadword ',6), (' chinese idiom ',5), (' play idiom ',5), (' open idiom ',4), (' i intention to see idiom ',4), (' idiom pattern ',4), (' what idiom ' is ',3), (' next idiom ',3) ].

cluster _ top _ texts [ (' chess ',45), (' chess holy ',6), (' play ',6), (' chess ',6), (' go ',5), (' chess lecture ',5), (' play high hand ',4), (' what ' chess ',4), (' layout skill of chess ',3), (' chess rule ',3), (' I see chess match ',3), (' how go ',3), (' how go ', 3).

In some embodiments, the first keyword or subject term corresponding to each cluster may be further output, and the query statement that appears most frequently in the cluster may be further output. The method can be specifically set according to actual requirements.

Illustratively, one output result is:

cluster _ top _ texts [ (' manual paper folding ',186), (' chinese painting ',98), (' shelf manual ',86), (' paper folding manual ',50), (' bear simple stroke ',46), (' manual dy ',31), (' manual lesson ',26), (' mother's handsheet ',23), (' plasticine manual ',20), (' method of making bubble gum ',18), (' self-made bubble gum ',17), (' manual plasticine ',16), (' paper folding prince ',16), (' art painting ',15), (' how to make bubble gum ',14), (' plasticine making ',14), (' paper folding frog ',14), (' plasticine ',12), (' colormud manual ',11) ]

"id"; hand "; [ cluster _ tfidf _ key, cluster _ top1_ texts ] [ 'origami', 'Manual origami' ]

cluster _ top _ texts [ (' discount ',74), (' benefit ',58), (' Low price ',38), (' package ',30), (' promotion ',25), (' cost ',20), (' Special price ',20), (' Offer ',15), (' Recall ',14), (' Utility ',12), (' selling price ',10), (' original price ',9), (' more benefit ',8), (' Special sale ',8), (' Current thousand, 5), (' discount ',5), (' monovalent ',4) ]

"id": preferential, [ cluster _ tfidf _ key, cluster _ top1_ texts ] [ 'preferential', 'reduced value', 'discounted' ]

cluster _ top _ texts [ ('penalty', 16), ('penalty', 5), ('jump', 5), ('dunk', 4), ('go-basket', 3), ('five penalty', 3) ]

"id": penalty ball, [ cluster _ tfidf _ key, cluster _ top1_ texts ] [ 'penalty ball', 'jump', 'penalty ball' ]

cluster _ top _ texts [ (' complex vowels ',24), (' english phonetic symbol ',11), (' initial and vowels ',8), ('23 initial, 6), ('24 vowels ',6), (' stroke by ' 5), (' six single vowels ',5), (' which of the word by the handle ',5), (' which of the word by the fire ',4), ('26 initial, 4), (' octant, 4), (' initial and vowel whole recognition table ',3), (' radical side radicals ',3), (' polyphone of the medicine word is ' 3) ]

"id": vowel ", [ cluster _ tfidf _ key, cluster _ top1_ texts ] [ 'initial', 'vowel', 'Complex vowel' ]

Wherein, cluster _ tfidf _ key represents the key words extracted based on the TF-IDF algorithm, and cluster _ top1_ texts represents the query statement with the largest occurrence number in the cluster.

In some embodiments, the related information of each cluster may also be output in a table form, as shown in table 1, table 1 is only an exemplary illustration, and in practical applications, more clusters may be included.

TABLE 1

Based on the processing method of the user log provided by the embodiment of the application, new requirements of the user can be mined from the user log (for example, the user needs to search for songs with lyrics, and the lyrics are wrongly described, for example, i can be changed into a situation that you are in star protection-i wants to find you), a statement that a vertical domain is not covered can be found, a vertical domain analysis error can be found, a tag system can be perfected, a lack of tag data of a database can be found, wrong statements of some popular movie and television music names can be found, some popular hot-door main broadcasts can be found, some specific crowd requirements (such as postpartum recovery, pregnancy and baby rearing) can be found, user simple daily English is used for man-machine interaction (such as yes and thank _ you), some new trendy things (such as bubble gum) can be found, and the like.

By regularly mining the new requirements of the user logs, the method can provide help for text analysis and service positioning of the semantic engine, is beneficial to improving the semantic analysis capability, enables the semantic engine to continuously grow in an iterative manner, forms virtuous circle, realizes quick response to the user requirements, and effectively reduces the human input.

Yet another embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the processor executes the computer-executable instructions, the method provided in any one of the above embodiments is implemented.

It should be noted that the computer-readable storage medium has the same advantages as the above embodiments, and is not described herein again.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An apparatus for processing a user log, comprising: a processor;

the processor configured to:

determining a new requirement based on the first query statement;

2. The apparatus of claim 1, wherein the processor is further configured to:

the treatment appliance is configured to:

3. The apparatus of claim 2, wherein the treatment appliance is configured to:

acquiring a target query statement in a user log;

4. The apparatus of claim 3, wherein the treatment appliance is configured to:

5. The apparatus of claim 3, wherein the treatment appliance is configured to:

6. The apparatus of claim 3, wherein the treatment appliance is configured to:

7. The apparatus of claim 3, wherein the processor is further configured to: determining a first keyword corresponding to each cluster according to a first query statement included in each cluster;

8. The apparatus of claim 7, wherein the treatment appliance is configured to:

9. The apparatus of claim 8, wherein the processor is further configured to: determining a second keyword in a group of words corresponding to the cluster by adopting a second keyword extraction algorithm; determining subject terms corresponding to the clusters based on the second keywords and the first keywords corresponding to the clusters;

10. A method for processing a user log, comprising:

determining a new requirement based on the first query statement;