CN117112728A

CN117112728A - Index query method, index query device, electronic equipment and storage medium

Info

Publication number: CN117112728A
Application number: CN202311047973.6A
Authority: CN
Inventors: 甄真; 徐志明; 惠向波; 杨冰霜
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-08-18
Filing date: 2023-08-18
Publication date: 2023-11-24

Abstract

The disclosure provides an index query method, an index query device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and particularly relates to the technical fields of deep learning, natural language processing and large language models. The method comprises the following steps: acquiring a spoken initial text; converting the initial text to obtain a target text which is not spoken; querying the value of at least one target index based on the target text. Therefore, only the initial text of the spoken language is required to be obtained, the initial text can be automatically converted into the target text of the non-spoken language, and the value of at least one target index is inquired, compared with the problem that the input index inquiry parameters are wrong and lead to index inquiry failure in the related technology, the method and the device support the spoken language input, greatly reduce the difficulty and the workload of index inquiry, improve the index inquiry efficiency and accuracy, and are suitable for index inquiry scenes of a distributed system.

Description

Index query method, index query device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly, to the field of deep learning, natural language processing, and large language model technologies, and more particularly, to an index query method, apparatus, electronic device, storage medium, and computer program product.

Background

At present, along with the continuous development of artificial intelligence technology, a large language model has the advantages of good generalization and the like, and is widely applied to the fields of information extraction, text classification, machine translation and the like. In the index query method in the related art, most of the index query methods need users to accurately input parameters of index query, if the input parameters of index query are wrong, the index query fails, and the problems of high difficulty and workload of index query, and high index query efficiency and accuracy exist.

Disclosure of Invention

The present disclosure provides an index query method, an index query device, an electronic device, a storage medium, and a computer program product.

According to a first aspect of the present disclosure, an index query method is provided, including: acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index; converting the initial text to obtain a target text which is not spoken; and inquiring the value of at least one target index based on the target text.

According to a second aspect of the present disclosure, there is provided an index query device, including: the acquisition module is used for acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index; the conversion module is used for converting the initial text to obtain a non-spoken target text; and the query module is used for querying the value of at least one target index based on the target text.

According to a third aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the index query method set forth in the first aspect above.

According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the index query method set forth in the first aspect above is provided.

According to a fifth aspect of the present disclosure, a computer program product is presented, comprising a computer program which, when executed by a processor, implements the index query method presented in the first aspect above.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a flow chart of an index query method according to an embodiment of the disclosure;

FIG. 2 is a flowchart of an index query method according to another embodiment of the disclosure;

FIG. 3 is a flowchart of an index query method according to another embodiment of the disclosure;

FIG. 4 is a flowchart of an index query method according to another embodiment of the disclosure;

FIG. 5 is a schematic diagram of a structure of an index query device according to an embodiment of the disclosure;

fig. 6 is a schematic block diagram of an electronic device of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

AI (Artificial Intelligence ) is a technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. At present, the AI technology has the advantages of high automation degree, high accuracy and low cost, and is widely applied.

DL (Deep Learning) is a new research direction in the field of ML (Machine Learning), and is an inherent rule and expression hierarchy of Learning sample data, so that a Machine can analyze Learning ability like a person, can recognize data such as characters, images and sounds, and is widely applied to speech and image recognition.

NLU (Natural Language Processing ) is an important direction in the field of computer science and artificial intelligence to study a computer system that can effectively implement natural language communication, and in particular, a science of software systems therein.

LLM (Large Language Model ) refers to a deep learning model trained using large amounts of text data that can generate natural language text or understand the meaning of language text. The large language model can process various natural language tasks, such as text classification, question-answering, dialogue and the like, and is an important path to artificial intelligence.

Fig. 1 is a flowchart of an index query method according to an embodiment of the disclosure. As shown in fig. 1, the method includes:

s101, acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index.

It should be noted that, the execution body of the index query method according to the embodiments of the present disclosure may be a hardware device having a data information processing capability and/or software necessary for driving the hardware device to operate. Alternatively, the execution body may include a workstation, a server, a computer, a user terminal, and other intelligent devices. The user terminal comprises, but is not limited to, a mobile phone, a computer, intelligent voice interaction equipment, intelligent household appliances, vehicle-mounted terminals and the like.

It should be noted that, the initial text is a spoken text, and is not limited too much, and may include text composed of at least one language of chinese, english, numerals, etc.

The target index is not limited too much. For example, taking the index query scenario of the distributed system as an example, the target index may include the number of requests, delay, status codes, etc. of services of the distributed system under the machine room. The services may include two-dimensional code services, data query services, data processing services, and the like. The machine room refers to a machine room for service deployment.

In an embodiment of the present disclosure, the initial text of the spoken language is obtained, including the following several possible implementations:

mode 1, acquiring an index query requirement of a user, and generating an initial text based on the index query requirement.

Therefore, the method can automatically generate the initial text in consideration of the index query requirement of the user.

It should be noted that, the index query requirement is not limited too much, for example, the initial identification of the spoken language of the target index, the initial time and/or the initial duration of the spoken language, etc. may be included. It should be noted that the initial identifier is not limited too much, and for example, the initial identifier may include a name, a number, or the like.

In some examples, continuing with the index query scenario of the distributed system as an example, the initial identification may include a spoken initial service name, an initial machine room name, and an initial index name. The initial service name, the initial machine room name, and the initial index name are used together to identify a unique target index.

For example, the initial identification of target index 1 may include a service, northern machine room, traffic. The service A is an initial service name, the northern machine room is an initial machine room name, and the flow is an initial index name. It can be understood that the target index 1 is the flow rate of the service a in the northern machine room.

For example, the initial identification of target index 2 may include a service, nanfang, delay. Wherein, the A service is an initial service name, nanfang is an initial machine room name, and delay is an initial index name. It will be appreciated that target index 2 is the delay of the a service in the southern computer room.

In some examples, generating the initial text based on the target query requirement may include combining an initial identification, an initial time, and/or an initial duration of the spoken language of the target to generate the initial text.

For example, if the index query requirements include "a", "northern machine room", "flow", "time-consuming", "10 am to 7 pm", the initial text "flow and time-consuming of 10 am to 7 pm northern machine room a" may be generated. Wherein, "A" is the initial service name, "10 am" and "7 pm" are all initial times.

For example, if the index query requirement includes "service a", "northern computer room", "flow rate", "last two hours", the initial text "flow rate of last two hours of service a in northern computer room" may be generated. Where "two hours" is the initial duration.

For example, if the index query requirements include "a", "B", "north machine room", "south machine room", "request count", "last two hours", the initial text "request count for north and south machine rooms a and B of last two hours" may be generated. Wherein "A" and "B" are initial service names.

In some examples, obtaining the index query requirement of the user includes receiving the index query requirement sent by the client. It may be understood that, taking the execution body of the index query method as an example of a server, the client may generate an index query requirement based on operation information (such as text input by the user, a clicked icon, and voice interaction information) of the user who controls the client, and send the index query requirement to the server, and correspondingly, the server may receive the index query requirement sent by the client.

Mode 2, receiving an initial text sent by a client.

Therefore, the method can receive the initial text sent by the client, namely, the initial text can be set by a user who controls the client, so that the initial text is more personalized.

It may be understood that, taking the execution body of the index query method as an example of a server, the client may generate an initial text based on operation information (such as a text input by a user, a clicked icon, voice information of the user, etc.) of the user who manipulates the client, and send the initial text to the server, and correspondingly, the server may receive the initial text sent by the client.

In some examples, the client may obtain voice information of a user who manipulates the client, and perform voice recognition on the voice information of the user to obtain the initial text.

For example, the user may input "i want to see the flow and response time index of the last 10 hours a in the south machine room" on the page of the client, and the client may use the text input by the user as the initial text, i.e., "i want to see the flow and response time index of the last 10 hours a in the south machine room" as the initial text. Wherein, "a" is an initial service name, "south machine room" is an initial machine room name, "10 hours" is an initial duration.

For example, the user may press a voice collection icon on the client and speak, the client may collect voice information of the user and perform voice recognition on the voice information to obtain a voice recognition result of "i want to see the flow and response time index of the last 10 hours a in the south machine room", and use "i want to see the flow and response time index of the last 10 hours a in the south machine room" as the initial text.

S102, converting the initial text to obtain a target text without spoken language.

It should be noted that the target text is a non-spoken text. The target text is not limited too much, and may include text composed of at least one language of chinese, english, numerals, etc.

It should be noted that the number of the target texts is at least one.

In the embodiment of the disclosure, the conversion of the initial text to obtain the target text without spoken language may include the following possible embodiments:

mode 1, converting a second spoken text segment in an initial text to obtain a non-spoken real text segment, and obtaining a target text based on the real text segment.

It is understood that the initial text may include at least one second text segment. The second text segment may include at least one term.

In some examples, the method further includes obtaining a third mapping relationship between the first candidate text segment and the real candidate text segment, and determining a real text segment after the second text segment conversion based on the third mapping relationship and the second text segment. For example, the true candidate text snippet mapped by the second text snippet may be used as the true text snippet converted by the second text snippet.

In some examples, obtaining the target text based on the real text snippets may include sequentially stitching the plurality of real text snippets to obtain the target text. It should be noted that the ordering of the plurality of real text segments is not excessively limited.

In some examples, before converting the spoken second text segment in the initial text, the method further includes segmenting the initial text to obtain a plurality of second text segments.

For example, the initial text is "I want to see the flow and response time index of the last 10 hours a in the south machine room", and the segmentation processing can be performed on the initial text to obtain the second text segment "10 hours", "a", "south machine room", "flow" and response time ".

If the current time is "2023-07-13:14:36:46", the "2023-07-13:14:36:46" may be used as the real text segment, and the "2023-07-13-14:36:46" may be converted to "10 hours" to obtain the real text segment "2023-07-13-04:36:46". Where "2023-07-13 04:36:46" is the start time and "2023-07-1314:36:46" is the end time.

The "a" may be converted to obtain the real text segment "a". Where "A" is the non-spoken real service name.

The south machine room can be converted to obtain a real text fragment "nf". Wherein, "nf" is a real machine room name that is not spoken.

The "flow" may be converted to obtain the real text segment "s_a_req_count". Where "s_a_req_count" is a non-spoken real index name.

The "response time" may be converted to obtain the real text segment "a_time". Where "a_time" is the real index name of the non-spoken language.

The target text (A, nf, s_a_req_count, 2023-07-1304:46, 2023-07-13-14:36:46) may be generated by sequentially stitching "A", "nf", "s_a_req_count", "2023-07-13:36:46".

The target text may be generated by sequentially stitching "A", "nf", "a_time", "2023-07-13:04:36:46", "2023-07-13:14:36:46" (A, nf, a_time, 2023-07-13:36:46, 2023-07-13:14:36:46).

And 2, converting the initial text according to the set text rule to obtain the target text.

It should be noted that, the set text rule refers to a text rule that the target text conforms to. The set text rule is not limited too much, and may include, for example, text format, text arrangement order, and the like. The text format may include, among other things, a value, date, time, text, etc.

S103, inquiring the value of at least one target index based on the target text.

It should be noted that, the target text is used for querying the value of at least one target index. For example, the number of the target texts is multiple, the target texts are in one-to-one correspondence with the target indexes, and the target texts are used for inquiring the values of the target indexes corresponding to the target texts.

In one embodiment, querying the value of the at least one target indicator based on the target text includes determining the at least one target indicator and a query time based on the target text, and querying the value of the at least one target indicator according to the query time. It will be appreciated that the query time is the real time of the non-spoken language, the query time includes the start time and the end time of the non-spoken language, and the query times of different target indexes may be the same or different.

For example, the target text is (A, nf, s_a_req_count,2023-07-13 04:36:46,2023-07-13 14:36:46), and the value of the unique index commonly identified by the real service name "A", the real machine room name "nf" and the real index name "s_a_req_count" at the end time of "2023-07-13:04:36:46" and the last 10 hours a in the south machine room "can be queried based on the target text.

For example, the target text is (A, nf, a_time,2023-07-13 04:36:46,2023-07-13 14:36:46), and the value of the unique index commonly identified by the real service name "A", the real machine room name "nf, and the real index name" a_time "under the conditions that the query start time is" 2023-07-13 04:36:46", and the end time is" 2023-07-13-14:36:46 ", namely, the value of the response time of the last 10 hours a in the south machine room is queried based on the target text.

In some examples, determining the at least one target indicator and the query time based on the target text includes obtaining a named entity of a real text segment in the target text, and determining the at least one target indicator and the query time based on the named entity of the real text segment.

It should be noted that the named entity is not limited too much, and for example, the named entity may include a real identifier, a start time, and an end time. The real identifier is not excessively limited, and the index query scene of the distributed system is taken as an example continuously, and the real identifier can comprise a non-spoken real service name, a real machine room name and a real index name. The real service name, the real machine room name, and the real index name are commonly used to identify a unique target index.

In some examples, obtaining named entities of real text segments in target text includes the following several possible implementations:

mode 1, determining a named entity of a real text segment based on the ordering of the real text segment in a target text.

For example, the target text is "real service name, real machine room name, real index name, start time, and end time", that is, the real service name is ranked 1 st, the real machine room name is ranked 2 nd, the real index name is ranked 3 rd, the start time is ranked 4 th, and the end time is ranked 5 th.

For example, if the target text is (A, nf, s_a_req_count, 2023-07-13:04:36:46, 2023-07-1314:36:46), the ranking of the real text segment "A" is 1 st, then "A" is the real service name, the ranking of the real text segment "nf" is 2 nd, then "nf" is the real machine room name, the ranking of the real text segment "A" is 1 st, then "A" is the real service name, the ranking of the real text segment "s_a_req_count" is 3 rd, then "s_a_req_count" is the real index name, the ranking of the real text segment "2023-07-13:04:36:46" is 4 th, then "2023-07-13:36:46" is the start time, the ranking of the real text segment "2023-07-14:36:46" is 5 th, and then "2023-07-13-14:36:46" is the end time.

And 2, carrying out named entity recognition on the target text, and determining the named entity of the real text fragment in the target text.

It should be noted that, the NER (Named Entity Recognition ) may be implemented by any named entity recognition method in the related art, which is not limited herein.

In some examples, determining at least one target indicator based on the named entity of the segment of real text includes determining the target indicator from a plurality of candidate indicators based on at least one non-spoken real identification. For example, continuing with the index query scenario of the distributed system, the target index may be determined from a plurality of candidate indexes based on the real service name, the real machine room name, and the real index name.

In some examples, the query time is determined based on a named entity of the real text snippet, including taking the real text snippet as a start time if the named entity of the real text snippet is a start time and taking the real text snippet as an end time if the named entity of the real text snippet is an end time.

According to the index query method, the initial text of the spoken language is obtained, wherein the initial text is used for querying the value of at least one target index, the initial text is converted to obtain the target text of the non-spoken language, and the value of the at least one target index is queried based on the target text. Therefore, only the initial text of the spoken language is required to be obtained, the initial text can be automatically converted into the target text of the non-spoken language, and the value of at least one target index is inquired, compared with the problem that the input index inquiry parameters are wrong and lead to index inquiry failure in the related technology, the method and the device support the spoken language input, greatly reduce the difficulty and the workload of index inquiry, improve the index inquiry efficiency and accuracy, and are suitable for index inquiry scenes of a distributed system.

In the above embodiment, regarding the conversion of the initial text in step S102 to obtain the target text without spoken language, as can be further understood with reference to fig. 2, fig. 2 is a schematic flow chart of an index query method according to another embodiment of the disclosure, as shown in fig. 2, the method includes:

s201, acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index.

For the relevant content of step S201, refer to the above embodiment, and will not be described herein.

S202, converting the initial identification of the spoken language in the initial text to obtain the real identification of the non-spoken language.

It should be noted that the initial text includes an initial identification of the spoken language. The content of the initial identifier and the real identifier can be referred to the above embodiments, and will not be described herein.

In one embodiment, the method includes converting an initial identifier of the spoken language in the initial text to obtain a real identifier of the non-spoken language, including converting an initial service name of the spoken language in the initial text to obtain a real service name of the non-spoken language, and converting an initial machine room name of the spoken language in the initial text to obtain a real machine room name of the non-spoken language. Therefore, the initial service name and the initial machine room name can be converted to obtain the real service name and the real machine room name.

In one embodiment, the method includes converting the initial spoken identifier in the initial text to obtain a non-spoken real identifier, and converting the initial spoken indicator name in the initial text to obtain a non-spoken real indicator name. Therefore, the initial index name can be converted to obtain the real index name.

In one embodiment, the method further includes obtaining a second mapping between the initial candidate identifier and the real candidate identifier, and determining the real identifier after the conversion of the initial identifier based on the second mapping and the initial identifier. For example, the real candidate identifier mapped by the initial identifier is used as the real identifier after the conversion of the initial identifier. Thus, the second mapping relationship may be preconfigured to determine the real identity.

For example, the second mapping relationship between the initial candidate service name and the real candidate service name is shown in table 1.

TABLE 1 second mapping between initial candidate service names and real candidate service names

True candidate service name	Initial candidate service name
		A	A. a, service A, A service, A module, module A
B	B. B, service B, B service, B module, module B

For example, the second mapping relationship between the initial candidate room name and the real candidate room name is shown in table 2.

Table 2 second mapping relationship between initial machine room name candidate and real machine room name candidate

Real candidate machine room name	Initial candidate machine room name
		bf	North, north machine room, beifang, north machine room, north
nf	South, south machine room, nanfang, south machine room, south

For example, the second mapping relationship among the real candidate service name, the initial candidate index name, and the real candidate index name is shown in table 3.

TABLE 3 second mapping relationship between real candidate service name, initial candidate index name, and real candidate index name

For example, if the initial text is "i want to see the traffic and response time index of the last 10 hours a in the south machine room", the initial identifier includes an initial service name "a", an initial machine room name "south machine room", an initial index name "traffic", and an initial index name "response time".

The initial service name "a" may be converted to obtain the real service name "a".

The original machine room name "south machine room" can be converted to obtain the real machine room name "nf".

The initial index name "flow" may be converted to obtain the real index name "s_a_req_count".

The initial index name "response time" may be converted to obtain the real index name "a_time".

For example, if the initial text is "b flow nf", the initial identifier includes an initial service name "b", an initial machine room name "nf", and an initial index name "flow".

The initial service name "B" may be converted to obtain the real service name "B".

The original machine room name "nf" can be converted to obtain the real machine room name "nf".

The initial index name "flow" may be converted to obtain the real index name "b_flow".

And S203, obtaining the target text based on the real identification.

In one embodiment, the real identifier includes a real service name, a real machine room name, and a real index name, and the target text is obtained based on the real identifier, and the target text is obtained by sequentially splicing the real service name, the real machine room name, and the real index name.

In one embodiment, obtaining the target text based on the real identifier includes obtaining an initial time and/or an initial duration of the spoken language in the initial text, obtaining a query time based on at least one of the initial time, the initial duration, the current time, and the reference duration, and obtaining the target text based on the real identifier and the query time. Thus, the query time can be obtained in consideration of at least one of the initial time, the initial time length, the current time and the reference time length, and the target text can be obtained based on the real identification and the query time.

It should be noted that the reference time period is not limited too much, and may be 1 hour, for example.

In some examples, deriving the query time based on at least one of the initial time, the initial duration, the current time, and the reference duration may include the following possible implementations:

in mode 1, if the initial time includes a first time and a second time, the first time is earlier than the second time, the first time is converted to obtain a start time, and the second time is converted to obtain an end time.

For example, if the initial text is "a flow and time consumption, the north machine room, 10 am, to 7 pm", the initial time may be obtained including "10 am", "7 pm", where "10 am" is the first time, and "7 pm" is the second time, if the current date is 2023, 7 month and 12, the "10 am" may be converted to obtain "2023-07-12, 10:00:00" as the start time, and "7 pm" may be converted to obtain "2023-07-12, 19:00:00" as the end time.

And 2, if the initial text comprises an initial time and an initial duration, converting the initial time to obtain a starting time, and taking the result of adding the initial duration to the starting time as an ending time.

For example, if the initial text is "the traffic of nf machine room a and b, the one hour range from 9 am", the initial time may be "9 am", the initial duration is "one hour", if the current date is 2023, 7, 12 months, the "9 am" may be converted to obtain "2023-07-12, 09, 00" as the start time, and the result "2023-07-12, 10, 00", obtained by adding the initial duration, as the end time.

And 3, if the initial text only comprises the initial duration, converting the current time to obtain the end time, and taking the result of subtracting the initial duration from the end time as the start time.

For example, if the initial text is "i want to see the flow and response time index of the last 10 hours a in the south machine room", the initial duration may be obtained as "10 hours", the current time "2023 year 7 month 13 afternoon 14 minutes and 46 seconds" may be converted to obtain "2023-07-13:14:36:46" as the end time, and the result "2023-07-13-04:36:46" obtained by subtracting the initial duration from the end time is obtained as the start time.

And 4, if the initial text does not comprise the initial time and the initial duration, converting the current time to obtain the end time, and taking the result of subtracting the reference duration from the end time as the start time.

For example, if the initial text is "b flow nf" and the reference time is 1 hour, the current time "2023, 7, 13, 10 am, 36 minutes, 46 seconds" may be converted to obtain "2023-07-13, 10:36:46" as the end time, and the result "2023-07-13, 09:36:46" obtained by subtracting the reference time from the end time is obtained as the start time.

In some examples, the real identifier includes a real service name, a real machine room name, and a real index name, the query time includes a start time and an end time, and the target text is obtained based on the real identifier and the query time, including sequentially splicing the real service name, the real machine room name, the real index name, the start time, and the end time to obtain the target text. Therefore, the sequential splicing of the real service name, the real machine room name, the real index name, the starting time and the ending time can be realized, and the ordering order of a plurality of real text fragments in the target text is ensured.

For example, if the initial text is "i want to see the traffic and response time index of the last 10 hours a in the south machine room", the real identifier includes a real service name "a", a real machine room name "nf", a real index name "s_a_req_count", a real index name "a_time", and the query time includes a start time "2023-07-13:04:36:46" and an end time "2023-07-13-14:36:46".

The target text (A, nf, s_a_req_count, 2023-07-1304:46, 2023-07-13-14:36:46) may be obtained by sequentially stitching "A", "nf", "s_a_req_count", "2023-07-13:36:46".

The target text (A, nf, a_time, 2023-07-13:36:46, 2023-07-1314:36:46) may be obtained by sequentially stitching "A", "nf", "a_time", "2023-07-13:04:36:46", "2023-07-1314:36:46".

For example, if the initial text is "B flow nf", the real identifier includes a real service name "B", a real machine room name "nf", a real index name "b_flow", the query time includes a start time "2023-07-1309:36:46", and an end time "2023-07-13 10:36:46", and the "B", "nf", "b_flow", "2023-07-1309:36:46", and "2023-07-13:10:36:46" may be sequentially spliced to obtain the target text (B, nf, b_flow, 2023-07-13:09:36:46, 2023-07-13:10:36:46).

S204, inquiring the value of at least one target index based on the target text.

For the relevant content of step S204, refer to the above embodiment, and will not be described herein.

According to the index query method, the initial spoken identifier in the initial text is converted to obtain the real non-spoken identifier, and the target text is obtained based on the real identifier. Therefore, the method and the device can automatically convert the initial spoken identifier into the real non-spoken identifier so as to obtain the target text, and compared with the prior art that a user is required to accurately input the real identifier, the method and the device support the input of the initial spoken identifier, greatly reduce the difficulty and workload of index query, improve the efficiency and accuracy of index query, and are suitable for index query scenes of a distributed system.

In the above embodiment, regarding obtaining the target text based on the real identifier in step S203, it can be further understood with reference to fig. 3, and fig. 3 is a flow chart of an index query method according to another embodiment of the disclosure, as shown in fig. 3, the method includes:

s301, acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index.

S302, converting the spoken initial service name in the initial text to obtain a non-spoken real service name.

S303, converting the spoken initial machine room name in the initial text to obtain a non-spoken real machine room name.

For the relevant content of steps S301-S303, refer to the above embodiments, and are not repeated here.

S304, obtaining candidate texts based on the real service names, the real machine room names and the spoken initial index names in the initial texts.

In one embodiment, the candidate text is obtained based on the real service name, the real machine room name and the spoken initial index name in the initial text, including sequentially stitching the real service name, the real machine room name and the initial index name to obtain the candidate text.

In one embodiment, candidate texts are obtained based on the real service name, the real machine room name and the spoken initial index name in the initial texts, wherein the candidate texts comprise acquisition start time and inquiry time, and the real service name, the real machine room name, the initial index name, the start time and the end time are spliced sequentially to obtain the candidate texts.

It should be noted that, the acquisition start time and the inquiry time may be referred to the above embodiments, and are not described herein.

For example, if the initial text is "i want to see traffic and response time index of the last 10 hours a in the south machine room", the real identifier includes a real service name "a", a real machine room name "nf", the initial index name includes "traffic", "response time", and the inquiry time includes a start time "2023-07-13-04:36:46", and an end time "2023-07-1314:36:46".

The candidate text (A, nf, flow,2023-07-13 04:36:46,2023-07-13 14:36:46) may be spliced sequentially for "A", "nf", "flow", "2023-07-13:36:46".

The candidate text (A, nf, response time, 2023-07-1304:36:46, 2023-07-13-14:36:46) may be spliced sequentially for "A", "nf", "response time", "2023-07-13:36:46".

For example, if the initial text is "B flow nf", the real identifier includes a real service name "B", a real machine room name "nf", the initial index name includes "flow", the query time includes a start time "2023-07-1309:36:46", and an end time "2023-07-13:36:46", and the "B", "nf", "flow", "2023-07-1309:36:46", and "2023-07-13:36:46" may be sequentially spliced to obtain candidate texts (B, nf, flow, 2023-07-1309:46, 2023-07-13:36:36:46).

And S305, obtaining a target text based on the candidate text.

In one embodiment, obtaining the target text based on the candidate text includes obtaining a query time, and obtaining the target text based on the candidate text and the query time.

In one embodiment, a target text is obtained based on the candidate text, including converting an initial index name in the candidate text to obtain a non-spoken real index name, and replacing the initial index name in the candidate text with the real index name to obtain the target text. Therefore, the initial index names can be converted to obtain real index names, and the initial index names in the candidate texts are replaced by the real index names to obtain target texts, so that the degree of the spoken language of the target texts is lower.

In some examples, the method further includes determining a target service from the plurality of candidate services based on the real service names in the candidate text, obtaining a first mapping relationship between an initial candidate index name and the real candidate index name under the target service, and determining a real index name after conversion of the initial index name based on the first mapping relationship and the initial index name. Therefore, the real index name is determined only according to the first mapping relation and the initial index name under the target service, the first mapping relation under all the services is not needed to be utilized, the acquisition range of the real index name is reduced, and the acquisition efficiency of the real index name is improved.

For example, if the candidate text is (a, nf, traffic, 2023-07-13:04:36:46, 2023-07-13:14:36:46), the target service may be determined to be service a based on the real service name "a", and a first mapping relationship between the initial candidate index name and the real candidate index name under service a may be obtained, and table 3 is taken as an example, where the first mapping relationship is the contents of rows 2 and 3 in table 3, and the real candidate index name "s_a_req_count" mapped by the initial index name "traffic" may be obtained as the real index name after the initial index name "traffic" is converted.

For example, if the candidate text is (a, nf, response time, 2023-07-13:04:36:46, 2023-07-13:14:36:46), the target service may be determined to be service a based on the real service name "a", and a first mapping relationship between the initial candidate index name and the real candidate index name under service a may be obtained, and the first mapping relationship is the contents of rows 2 and 3 in table 3, for example, and the real candidate index name "a_time" mapped by the initial index name "response time" may be obtained as the real index name after the conversion of the initial index name "response time".

For example, if the candidate text is (B, nf, flow, 2023-07-13:36:46, 2023-07-13:10:36:46), the target service may be determined to be the service B based on the real service name "B", and a first mapping relationship between the initial candidate index name and the real candidate index name under the service B may be obtained, and the first mapping relationship is the contents of lines 4 and 5 in table 3, for example, and the real candidate index name "b_flow" mapped by the initial index name "folw" may be obtained as the real index name after the initial index name "flow" is converted.

S306, inquiring the value of at least one target index based on the target text.

For the relevant content of step S306, refer to the above embodiment, and will not be described herein.

According to the index query method, candidate texts are obtained based on the real service names, the real machine room names and the spoken initial index names in the initial texts, and target texts are obtained based on the candidate texts. Therefore, the candidate text can be obtained by comprehensively considering the real service name, the real machine room name and the initial index name, so as to obtain the target text.

On the basis of any of the above embodiments, the method further includes performing named entity recognition on the initial text, determining at least one spoken language initial identifier in the initial text, and determining a target indicator from a plurality of candidate indicators based on the at least one initial identifier, so as to achieve determination of the target indicator.

It should be noted that, the named entity recognition of the initial text may be implemented by any named entity recognition method in the related art, which is not limited herein.

In some examples, continuing with the index query scenario of the distributed system as an example, the initial identification includes an initial service name, an initial machine room name, and an initial index name, and the target index is determined from the plurality of candidate indexes based on the at least one initial identification, including the target index may be determined from the plurality of candidate indexes based on the initial service name, the initial machine room name, and the initial index name.

In the above embodiment, regarding the conversion of the initial text in step S102 to obtain the target text without spoken language, it can be further understood with reference to fig. 4, and fig. 4 is a schematic flow chart of an index query method according to another embodiment of the disclosure, as shown in fig. 4, the method includes:

s401, acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index.

For the relevant content of step S401, refer to the above embodiment, and will not be described herein.

S402, determining a total query task corresponding to the initial text, wherein the total query task is used for querying the values of at least two target indexes.

In one embodiment, determining the total query task corresponding to the initial text includes performing semantic analysis on the initial text to obtain the total query task.

In one embodiment, determining the total query task corresponding to the initial text includes determining at least one target indicator, and obtaining the total query task based on the at least one target indicator. It should be noted that, for the relevant content of determining the target index, reference may be made to the above embodiment, and details are not repeated here.

S403, splitting the total query task to obtain a plurality of sub-query tasks, wherein the sub-query tasks are in one-to-one correspondence with the target indexes.

It should be noted that, the sub-query task is used to query the value of a target index. Target indexes corresponding to different sub-query tasks are different.

For example, if the initial text is "the flow and time consumption of a", the north machine room is 10 am, and the afternoon is 7 pm ", semantic analysis can be performed on the initial text to obtain the total query task of" the flow and time consumption of the north machine room a from 10 am to 7 pm ". The total query task can be split, and the sub-query tasks comprise flow of the machine room a from 10 am to 7 pm and time consumption of the machine room a from 10 am to 7 pm.

For example, if the initial text is "the traffic of nf rooms a and b, the one hour range from 9 am", semantic analysis may be performed on the initial text to obtain the traffic of nf rooms a and b, where the total query task is "the one hour range from 9 am". The total query task can be split to obtain sub-query tasks including 'the flow of the service of the nf machine room a within an hour range from 9 am', 'the flow of the service of the nf machine room b within an hour range from 9 am'.

For example, if the initial text is (b, south, flow,9 points, 10 points) (north machine room, a service, delay, 10:01:01, 12:00:00), semantic analysis may be performed on the initial text to obtain a total query task of "flow of 9 points to 10 points south machine room b, delay of 10:01:01 to 12:00:00 north machine room a service". The total query task can be split, and the sub-query tasks comprise 'flow of 9-point to 10-point southern machine room b', 'delay of 10:01:01 to 12:00:00 northern machine room a service'.

For example, if the initial text is "i want to see the flow and response time index of the last 10 hours a in the south machine room", semantic analysis may be performed on the initial text to obtain the flow and response time index of the total query task "the last 10 hours a in the south machine room". The total query task can be split, and the sub-query task comprises a flow index of the last 10 hours a in the south machine room and a response time index of the last 10 hours a in the south machine room.

S404, converting the initial text based on the sub-query task to obtain a target text corresponding to the sub-query task.

In the embodiment of the disclosure, sub-query tasks are in one-to-one correspondence with target text. Different sub-query tasks correspond to different target text.

In one embodiment, based on the sub-query task, converting the initial text to obtain a target text corresponding to the sub-query task, including obtaining a real identifier corresponding to the sub-query task, and replacing the initial identifier in the initial text with the real identifier corresponding to the sub-query task to obtain the target text.

In some examples, a fourth mapping relationship between the sub-candidate query task and the real candidate identifier may be obtained, and the real identifier corresponding to the sub-query task is determined based on the fourth mapping relationship and the sub-query task.

In one embodiment, based on the sub-query task, converting the initial text to obtain a target text corresponding to the sub-query task, including extracting a first text segment associated with the sub-query task from the initial text, and converting the first text segment to obtain the target text corresponding to the sub-query task. Therefore, the first text fragments respectively associated with each sub-query task can be extracted from the initial text, and the first text fragments are converted to obtain the target text corresponding to the sub-query task, so that the target text corresponding to the sub-query task is obtained.

It should be noted that, converting the text segment to obtain the target text corresponding to the sub-query task may refer to converting the initial text to obtain the related content of the target text, which is not described herein again.

For example, if the initial text is "flow and time consumption of a", the north machine room is 10 am to 7 pm ", the sub-query task 1 is" flow of north machine room a from 10 am to 7 pm ", and the sub-query task 2 is" time consumption of north machine room a from 10 am to 7 pm ".

Based on the sub-query task 1, the first text segment "a", "flow", "north machine room", "10 am", "7 pm" associated with the sub-query task 1 may be extracted from the initial text. Converting "a" to obtain "A", converting "flow" to obtain "s_a_req_count", converting "north machine room" to obtain "bf", converting "10 am" to obtain "2023-07-12:00:00", and converting "7 pm" to obtain "2023-07-12:19:00:00". And (3) sequentially splicing the 'A', 'bf', 's_a_req_count', '2023-07-12:10:00', '2023-07-12:19:00:00', and obtaining target text (A, bf, s_a_req_count, 2023-07-12:10:00:00, 2023-07-12:19:00) corresponding to the sub-query task 1.

The first text segment "a", "time-consuming", "north machine room", "10 am", "7 pm" associated with the sub-query task 2 may be extracted from the above initial text based on the sub-query task 2. Converting "a" to obtain "A", converting "time consuming" to obtain "a_time", converting "north machine room" to obtain "bf", converting "10 am" to obtain "2023-07-12:10:00:00", and converting "7 pm" to obtain "2023-07-12:19:00:00". And (3) sequentially splicing the 'A', 'bf', 'a_time', '2023-07-1210:00:00', '2023-07-12:19:00:00', and obtaining target texts (A, bf, a_time, 2023-07-12:10:00:00, 2023-07-12:19:00:00) corresponding to the sub-query task 2.

S405, inquiring the value of the target index corresponding to the sub-inquiry task based on the target text corresponding to the sub-inquiry task.

For example, the values of the target indicators corresponding to sub-query task 1 may be queried based on the target text (A, bf, s_a_req_count,2023-07-1210:00:00, 2023-07-12:19:00) corresponding to sub-query task 1. It can be understood that the target index corresponding to the sub-query task 1 is a unique index commonly identified by a real service name "a", a real machine room name "bf", and a real index name "s_a_req_count".

For example, the target index corresponding to sub-query task 2 may be queried based on the target text (A, bf, a_time,2023-07-1210:00:00, 2023-07-12:19:00:00) corresponding to sub-query task 2. It can be understood that the target index corresponding to the sub-query task 2 is a unique index commonly identified by the real service name "a", the real machine room name "bf" and the real index name "a_time".

The index query method provided by the disclosure determines a total query task corresponding to an initial text, wherein the total query task is used for querying values of at least two target indexes, the total query task is split to obtain a plurality of sub-query tasks, the sub-query tasks are in one-to-one correspondence with the target indexes, the initial text is converted based on the sub-query tasks to obtain target texts corresponding to the sub-query tasks, and the values of the target indexes corresponding to the sub-query tasks are queried based on the target texts corresponding to the sub-query tasks. Therefore, the total query task can be split to obtain a plurality of sub-query tasks, the initial text is converted in consideration of the sub-query tasks to obtain target text corresponding to the sub-query tasks, the values of the target indexes corresponding to the sub-query tasks are queried, and the query of a plurality of target values can be realized.

On the basis of any of the above embodiments, converting the initial text in step S102 to obtain a target text that is not spoken includes inputting the initial text into a large language model, and outputting the target text from the large language model. Therefore, the initial text can be converted through the large language model, and the target text can be obtained.

On the basis of any of the above embodiments, step S103 further includes generating a target indicator curve based on the target indicator value after querying at least one target indicator value based on the target text, and displaying the at least one target indicator curve on the same page. Therefore, the automatic generation of the curves of the target indexes can be realized, the curves of at least one target index are displayed on the same page, the visual display of the indexes can be realized, and the user can conveniently view the curves.

In one embodiment, generating the curve of the target indicator based on the value of the target indicator includes obtaining a generation time of the value of the target indicator, generating coordinates of points on the curve of the target indicator based on the value of the target indicator and the generation time, and generating the curve of the target indicator based on the coordinates of a plurality of points on the curve of the target indicator.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

According to an embodiment of the present disclosure, the present disclosure further provides an index query device, which is configured to implement the index query method described above.

Fig. 5 is a block diagram of an index querying device according to an embodiment of the present disclosure.

As shown in fig. 5, the index query device 500 includes: an acquisition module 501, a conversion module 502, and a query module 503.

The obtaining module 501 is configured to obtain a spoken initial text, where the initial text is used to query a value of at least one target index;

the conversion module 502 is configured to convert the initial text to obtain a target text that is not spoken;

and a query module 503, configured to query the value of at least one target indicator based on the target text.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: converting the initial identification of the spoken language in the initial text to obtain a real identification of the non-spoken language; and obtaining the target text based on the real identification.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: converting the spoken initial service name in the initial text to obtain a non-spoken real service name; and converting the spoken initial machine room name in the initial text to obtain a non-spoken real machine room name.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: obtaining a candidate text based on the real service name, the real machine room name and the initial index name of the spoken language in the initial text; and obtaining the target text based on the candidate text.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: converting the initial index names in the candidate text to obtain non-spoken real index names; and replacing the initial index name in the candidate text with the real index name to obtain the target text.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: determining a target service from a plurality of candidate services based on the real service names in the candidate text; acquiring a first mapping relation between an initial candidate index name and a real candidate index name under the target service; and determining the real index name after the conversion of the initial index name based on the first mapping relation and the initial index name.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: acquiring a second mapping relation between the initial candidate identifier and the real candidate identifier; and determining the real identifier after the conversion of the initial identifier based on the second mapping relation and the initial identifier.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: determining a total query task corresponding to the initial text, wherein the total query task is used for querying the values of at least two target indexes; splitting the total query task to obtain a plurality of sub-query tasks, wherein the sub-query tasks are in one-to-one correspondence with the target indexes; and converting the initial text based on the sub-query task to obtain a target text corresponding to the sub-query task.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: extracting a first text segment associated with the sub-query task from the initial text; and converting the first text segment to obtain a target text corresponding to the sub-query task.

In one embodiment of the present disclosure, the query module 503 is further configured to: inquiring the value of a target index corresponding to the sub-inquiry task based on the target text corresponding to the sub-inquiry task.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: acquiring initial time and/or initial duration of spoken language in the initial text; obtaining inquiry time based on at least one of the initial time, the initial time length, the current time and the reference time length; and obtaining the target text based on the real identification and the query time.

In one embodiment of the present disclosure, the real identifier includes a real service name, a real machine room name, and a real index name, the query time includes a start time and an end time, and the conversion module 502 is further configured to: and sequentially splicing the real service name, the real machine room name, the real index name, the starting time and the ending time to obtain the target text.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: carrying out named entity recognition on the initial text, and determining at least one spoken initial identifier in the initial text; the target indicator is determined from a plurality of candidate indicators based on at least one of the initial identifications.

In one embodiment of the present disclosure, the conversion module 502 is further configured to: inputting the initial text into a large language model, and outputting the target text by the large language model.

In one embodiment of the present disclosure, after the querying, based on the target text, the value of at least one target index, the querying module 503 is further configured to: generating a curve of the target index based on the value of the target index; and displaying the curve of at least one target index on the same page.

The index query device provided by the disclosure obtains a spoken initial text, wherein the initial text is used for querying the value of at least one target index, converting the initial text to obtain a non-spoken target text, and querying the value of at least one target index based on the target text. Therefore, only the initial text of the spoken language is required to be obtained, the initial text can be automatically converted into the target text of the non-spoken language, and the value of at least one target index is inquired, compared with the problem that the input index inquiry parameters are wrong and lead to index inquiry failure in the related technology, the method and the device support the spoken language input, greatly reduce the difficulty and the workload of index inquiry, improve the index inquiry efficiency and accuracy, and are suitable for index inquiry scenes of a distributed system.

According to embodiments of the present disclosure, the present disclosure also proposes an electronic device, a readable storage medium and a computer program product.

Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 606, such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, such as the index query method. For example, in some embodiments, the index query method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When a computer program is loaded into RAM 603 and executed by computing unit 601, one or more steps of the index query method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the index query method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To address interactions with a user account, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user account; and a keyboard and pointing device (e.g., a mouse or trackball) through which a user account may present input to the computer. Other kinds of devices may also be used to propose interactions with a user account; for example, feedback presented to the user account may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user account may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user account computer having a graphical user account interface or a web browser through which a user account can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

According to an embodiment of the present disclosure, there is also provided a computer program product, including a computer program, where the computer program, when executed by a processor, implements the steps of the index query method according to the above embodiment of the present disclosure.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. An index query method, comprising:

acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index;

Converting the initial text to obtain a target text which is not spoken;

and inquiring the value of at least one target index based on the target text.

2. The method of claim 1, wherein said converting the initial text to a non-spoken target text comprises:

converting the initial identification of the spoken language in the initial text to obtain a real identification of the non-spoken language;

and obtaining the target text based on the real identification.

3. The method of claim 2, wherein the converting the spoken initial identifier in the initial text to obtain the non-spoken real identifier comprises:

converting the spoken initial service name in the initial text to obtain a non-spoken real service name;

and converting the spoken initial machine room name in the initial text to obtain a non-spoken real machine room name.

4. A method according to claim 3, wherein said deriving said target text based on said real identity comprises:

obtaining a candidate text based on the real service name, the real machine room name and the initial index name of the spoken language in the initial text;

And obtaining the target text based on the candidate text.

5. The method of claim 4, wherein the deriving the target text based on the candidate text comprises:

converting the initial index names in the candidate text to obtain non-spoken real index names;

and replacing the initial index name in the candidate text with the real index name to obtain the target text.

6. The method of claim 5, wherein the method further comprises:

determining a target service from a plurality of candidate services based on the real service names in the candidate text;

acquiring a first mapping relation between an initial candidate index name and a real candidate index name under the target service;

and determining the real index name after the conversion of the initial index name based on the first mapping relation and the initial index name.

7. The method of claim 2, wherein the method further comprises:

acquiring a second mapping relation between the initial candidate identifier and the real candidate identifier;

and determining the real identifier after the conversion of the initial identifier based on the second mapping relation and the initial identifier.

8. The method of claim 1, wherein said converting the initial text to a non-spoken target text comprises:

Determining a total query task corresponding to the initial text, wherein the total query task is used for querying the values of at least two target indexes;

splitting the total query task to obtain a plurality of sub-query tasks, wherein the sub-query tasks are in one-to-one correspondence with the target indexes;

and converting the initial text based on the sub-query task to obtain a target text corresponding to the sub-query task.

9. The method of claim 8, wherein the converting the initial text based on the sub-query task to obtain the target text corresponding to the sub-query task comprises:

extracting a first text segment associated with the sub-query task from the initial text;

and converting the first text segment to obtain a target text corresponding to the sub-query task.

10. The method of claim 8, wherein the querying the value of at least one of the target metrics based on the target text comprises:

inquiring the value of a target index corresponding to the sub-inquiry task based on the target text corresponding to the sub-inquiry task.

11. The method according to any one of claims 2-10, wherein the deriving the target text based on the real identification comprises:

Acquiring initial time and/or initial duration of spoken language in the initial text;

obtaining inquiry time based on at least one of the initial time, the initial time length, the current time and the reference time length;

and obtaining the target text based on the real identification and the query time.

12. The method of claim 11, wherein the real identifier includes a real service name, a real machine room name, and a real index name, the query time includes a start time and an end time, and the obtaining the target text based on the real identifier and the query time includes:

and sequentially splicing the real service name, the real machine room name, the real index name, the starting time and the ending time to obtain the target text.

13. The method of any of claims 1-10, wherein the method further comprises:

carrying out named entity recognition on the initial text, and determining at least one spoken initial identifier in the initial text;

the target indicator is determined from a plurality of candidate indicators based on at least one of the initial identifications.

14. The method of any of claims 1-10, wherein the converting the initial text to a non-spoken target text comprises:

Inputting the initial text into a large language model, and outputting the target text by the large language model.

15. The method according to any one of claims 1-10, wherein after querying the value of at least one target indicator based on the target text, further comprising:

generating a curve of the target index based on the value of the target index;

and displaying the curve of at least one target index on the same page.

16. An index query device, comprising:

the acquisition module is used for acquiring a spoken initial text, wherein the initial text is used for inquiring the value of at least one target index;

the conversion module is used for converting the initial text to obtain a non-spoken target text;

and the query module is used for querying the value of at least one target index based on the target text.

17. The apparatus of claim 16, wherein the conversion module is further configured to:

and obtaining the target text based on the real identification.

18. The apparatus of claim 17, wherein the conversion module is further configured to:

19. The apparatus of claim 18, wherein the conversion module is further configured to:

and obtaining the target text based on the candidate text.

20. The apparatus of claim 19, wherein the conversion module is further configured to:

21. The apparatus of claim 20, wherein the conversion module is further configured to:

22. The apparatus of claim 17, wherein the conversion module is further configured to:

23. The apparatus of claim 16, wherein the conversion module is further configured to:

24. The apparatus of claim 23, wherein the conversion module is further configured to:

25. The apparatus of claim 23, wherein the query module is further configured to:

26. The apparatus of any of claims 17-25, wherein the conversion module is further to:

27. The apparatus of claim 26, wherein the real identification comprises a real service name, a real machine room name, and a real index name, the query time comprises a start time and an end time, the conversion module is further configured to:

28. The apparatus of any of claims 16-25, wherein the conversion module is further to:

29. The apparatus of any of claims 16-25, wherein the conversion module is further to:

30. The apparatus of any of claims 16-25, wherein the query module, after querying the value of at least one of the target metrics based on the target text, is further to:

generating a curve of the target index based on the value of the target index;

and displaying the curve of at least one target index on the same page.

31. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-15.

32. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-15.

33. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-15.