CN113836288B - Method and device for determining service detection result and electronic equipment - Google Patents
Method and device for determining service detection result and electronic equipment Download PDFInfo
- Publication number
- CN113836288B CN113836288B CN202111416742.9A CN202111416742A CN113836288B CN 113836288 B CN113836288 B CN 113836288B CN 202111416742 A CN202111416742 A CN 202111416742A CN 113836288 B CN113836288 B CN 113836288B
- Authority
- CN
- China
- Prior art keywords
- session data
- detection
- matched
- keyword
- requirement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computer And Data Communications (AREA)
Abstract
The application provides a method and a device for determining a service detection result and electronic equipment, wherein the method for determining the service detection result comprises the following steps: acquiring at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched, which is related to the service detection requirement in a preset time period; determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword; for each piece of session data to be matched, determining a session data group to be matched corresponding to the session data to be matched according to the detection rule; screening a target conversation data group from the determined at least one conversation data group to be matched according to the detection rule; and determining a service detection result of the service detection requirement in the preset time period based on the number of the target session data groups. By the determining method and the determining device, the service detection result can be more accurately determined.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a method and an apparatus for determining a service detection result, and an electronic device.
Background
Under the condition of increasingly developed internet-based communication technology, users keep close text communication among a plurality of service platforms and companies. A large amount of textual communication between session-based users is generated, and the session-based session data contributes significantly to portraying users, analyzing customer behavior, or industry analysis. Based on the information, the enterprise can more flexibly and accurately achieve centralized and efficient allocation of resources, and the information is often required to be detected so as to determine a corresponding service detection result.
At present, the detection of session data usually needs to determine whether the session data meets the service monitoring requirements by means of information extraction and comparing extracted keywords, the meanings of some words are not fixed, but the detection method of information extraction can only monitor the keywords by comparing the one-sided mode, which results in inaccurate determined service detection results; therefore, how to accurately detect the session data becomes an urgent problem to be solved.
Disclosure of Invention
In view of this, an object of the present application is to provide a method, an apparatus and an electronic device for determining a service detection result, which can generate a corresponding detection rule according to a service detection requirement, and detect a plurality of pieces of session data to be matched with a contextual relationship by using the detection rule, so as to more accurately determine the service detection result of the service detection requirement.
In a first aspect, an embodiment of the present application provides a method for determining a service detection result, where the method for determining includes:
acquiring at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched, which is related to the service detection requirement in a preset time period;
determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword;
for each piece of session data to be matched, determining a session data group to be matched corresponding to the session data to be matched according to the detection rule, wherein the session data group to be matched comprises the session data to be matched and reference session data having a context relationship with the session data to be matched;
screening a target conversation data group from the determined at least one conversation data group to be matched according to the detection rule;
and determining a service detection result of the service detection requirement in the preset time period based on the number of the target session data groups.
Further, determining, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement, including:
determining a keyword identifier corresponding to each demand keyword, wherein the keyword identifier represents category information of the demand keyword;
adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword;
determining a logic operator of a keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection based on the service detection requirement;
and combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
Further, the determining, according to the detection rule, a session data group to be matched corresponding to each piece of session data to be matched includes:
for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship;
the session data to be matched are detected for the first time by utilizing a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions;
if so, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity;
and determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
Further, according to the detection rule, screening out a target session data group which accords with the detection target from the determined at least one session data group to be matched, wherein the target session data group comprises;
aiming at each piece of reference session data in each session data group to be matched, primarily detecting the reference session data by using a second detection sub-rule, and determining a sub-detection result of each keyword rule in the second detection sub-rule;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the reference session data meets secondary detection conditions;
and if so, determining the session data group to be matched to which the reference session data belongs as the target session data group.
Further, the determining, based on the number of the target session data sets, a service detection result of the service detection requirement in the preset time period includes:
determining the existence proportion of the session data to be matched which accords with the detection rule in the at least one piece of session data to be matched based on the number of the target session data group and the number of the at least one piece of session data to be matched;
and determining a service detection result of the service detection requirement in the preset time period based on the existence ratio.
In a second aspect, an embodiment of the present application further provides a device for determining a service detection result, where the device for determining a service detection result includes:
the system comprises an acquisition module, a matching module and a matching module, wherein the acquisition module is used for acquiring at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched, which is related to the service detection requirement in a preset time period;
the detection rule determining module is used for determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword;
the to-be-matched session data set determining module is used for determining a to-be-matched session data set corresponding to each piece of to-be-matched session data according to the detection rule, wherein the to-be-matched session data set comprises the to-be-matched session data and reference session data having a contextual relation with the to-be-matched session data;
the target session data set determining module is used for screening out a target session data set from the determined at least one session data set to be matched according to the detection rule;
and the service detection result determining module is used for determining the service detection result of the service detection requirement in the preset time period based on the number of the target session data groups.
Further, when the detection rule determining module is configured to determine, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement, the detection rule determining module is configured to:
determining a keyword identifier corresponding to each demand keyword, wherein the keyword identifier represents category information of the demand keyword;
adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword;
determining a logic operator of a keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection based on the service detection requirement;
and combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
Further, when the to-be-matched session data group determining module is configured to determine, for each piece of to-be-matched session data, a to-be-matched session data group corresponding to the to-be-matched session data according to the detection rule, the to-be-matched session data group determining module is configured to:
for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship;
the session data to be matched are detected for the first time by utilizing a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions;
if so, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity;
and determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine readable instructions being executed by the processor to perform the steps of the method for determining a traffic detection result as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for determining a service detection result as described above are performed.
The method for determining the service detection result includes the steps that firstly, at least one requirement keyword used for representing service detection requirements and at least one piece of session data to be matched related to the service detection requirements in a preset time period are obtained; then, determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword; for each piece of session data to be matched, determining a session data group to be matched corresponding to the session data to be matched according to the detection rule; screening a target conversation data group from the determined at least one conversation data group to be matched according to the detection rule; and finally, determining a service detection result of the service detection requirement in the preset time period based on the number of the target session data groups.
Compared with the prior art, the method and the device for determining the service detection result can generate the corresponding detection rule according to the service detection requirement, the used detection rule can detect single session data to be matched, multiple session data to be matched and session data to be matched based on the context relationship, and the detection rule has the advantages of less identification types, high universality and high cohesion. Meanwhile, the detection rule is based on understanding and abstraction of the service detection requirement, so that the readability and the writeability are high when the detection rule is written. Meanwhile, the staff can write the detection rules efficiently, the generation efficiency of the detection rules is improved, and the determination efficiency of the service detection results is further improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of a method for determining a service detection result according to an embodiment of the present application;
fig. 2 is a flowchart of a method for determining a detection rule according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a device for determining a service detection result according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. Every other embodiment that can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present application falls within the protection scope of the present application.
Under the condition of increasingly developed internet-based communication technology, users keep close text communication among a plurality of service platforms and companies. A large amount of textual communication between session-based users is generated, and the session-based session data contributes significantly to portraying users, analyzing customer behavior, or industry analysis. Based on the information, the enterprise can more flexibly and accurately achieve centralized and efficient allocation of resources, and the information is often required to be detected so as to determine a corresponding service detection result.
Research shows that at present, whether the session data meet the service monitoring requirements or not is often determined by comparing extracted keywords through an information extraction mode, the meanings of some words are not fixed, but the information extraction detection mode can only monitor the keywords through comparison in a one-sided mode, so that the determined service detection result is inaccurate; therefore, how to accurately detect the session data becomes an urgent problem to be solved.
Based on this, the embodiment of the application provides a method for determining a service detection result, which solves the problem that session data with a contextual relationship cannot be detected in the prior art, and improves the accuracy of the determined service detection result.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for determining a service detection result according to an embodiment of the present disclosure. As shown in fig. 1, a method for determining a service detection result provided in an embodiment of the present application includes:
s101, at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched related to the service detection requirement in a preset time period are obtained.
It should be noted that the service detection requirement refers to a service index provided by a user and used for detecting within a preset time period, and the requirement keyword refers to a keyword determined according to the service detection requirement, and the requirement keyword may represent the service detection requirement. The session data to be matched refers to process data generated by information communication through an instant messaging tool, and the form of the session data to be matched can include but is not limited to: text conversation information, mail information, voice call information, video call information, and the like. When the session data to be matched is voice call information or video call information, text conversion needs to be performed on the voice call information or the video call information to generate text-form session data to be matched, and here, how to convert the voice call information or the video call information into text-form session data to be matched is described in detail in the prior art, and redundant description is not repeated here. The preset time period may be preset as needed, for example, the preset time period is set to 00:00-24:00, then, for the service detection requirement, all the session data to be matched related to the service detection requirement in the time period from 00:00 to 24:00 are acquired, or the preset time period may be set to another time period, such as a week, a month, and the like, which is not limited by the applicant.
For the above step S101, in a specific implementation, a user may set a service detection requirement by himself, for example, the service detection requirement may be "whether a service for sale is violated" or "whether a customer is interested in a medicine". And then determining at least one requirement keyword for representing the service detection requirement based on the service detection requirement set by the user. As an example, when a customer asks for a sale of a certain product "with or without" and when the sale answer "without", the service of the sale is considered to have a violation, and when the service detection requirement is "whether the service of the sale is violated", the requirement keyword for characterizing the service detection requirement may be several words of "customer", "with or without", "sale" and "without". When a customer asks for sale of "cold drug is present or absent", the customer is considered to be interested in the drug, and when the business detection requirement is "whether the customer is interested in the drug", the requirement keywords for characterizing the business detection requirement may be "customer", "present or absent", and "drug". After at least one requirement keyword is determined, at least one piece of session data to be matched related to each requirement keyword in a preset time period is obtained.
Here, it should be noted that the above examples of the service detection requirement and requirement keyword are only examples, and in practice, the service detection requirement and requirement keyword are not limited to the above examples.
S102, determining a detection rule for analyzing the detection target indicated by the service detection requirement according to the at least one requirement keyword.
It should be noted that the detection target indicated by the service detection requirement refers to an object to be detected in the service detection requirement, for example, the detection target may be a specific user, and the detection target may also be a keyword. The detection rule refers to a rule grammar, similar to a programming language or a script language, and is generally a rule formed by splicing keywords and characters (symbols, letters, numbers and the like).
For the above step S102, in a specific implementation, after at least one requirement keyword for characterizing a service detection requirement is determined, a detection rule for analyzing a detection target indicated by the service detection requirement is determined according to the at least one requirement keyword.
Referring to fig. 2, fig. 2 is a flowchart of a method for determining a detection rule according to an embodiment of the present disclosure. As shown in fig. 2, for the step S102, the determining, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement includes:
s201, aiming at each requirement keyword, determining a keyword identification corresponding to the requirement keyword.
Wherein the keyword identification represents category information of the demand keyword.
It should be noted that the keyword identifier refers to an identifier used for constructing the detection rule. Specifically, the keyword identifier of the demand keyword is determined according to the category information of the demand keyword, where the demand keyword may include a single keyword, a composite keyword and a user keyword, when the category of the demand keyword is the single keyword, the corresponding keyword identifier is the single keyword identifier, when the category of the demand keyword is the composite keyword, the corresponding keyword identifier is the composite keyword, and when the demand keyword is the user keyword, the corresponding keyword identifier is the user keyword identifier.
In the following, each category requirement keyword and the keyword identifier corresponding to each category requirement keyword are exemplified:
the single keyword refers to a keyword predefined by a user, and the single keyword is a single phrase or word or a plurality of characters without compound attributes. For example, the single keyword may be a keyword such as "have or not", "you are", "goodbye", "welcome", and the like. When the requirement keyword is a single keyword, a single keyword identification corresponding to the requirement keyword may be represented using two symbols of "[" and "]".
A compound keyword refers to a keyword having a compound attribute, and may be composed of a phrase or a word or several characters. For example, there are many keywords belonging to "medicine", such as "cold medicine", "antipyretic", and "scald ointment", and thus, the composite keyword may be a keyword having composite attributes such as "medicine", "food", "daily necessities", and "cosmetics". When the requirement keyword is a composite keyword, the identification of the composite keyword corresponding to the requirement keyword can be represented by two symbols of "<" and ">".
The user keywords are keywords for characterizing a sender of session data to be matched, for example, the session data to be matched is sent by zhang san, the "zhang san" is the user keywords, the session data to be matched is sent by sale, and the "sale" is the user keywords. When the requirement keyword is a user keyword, the user keyword identifier corresponding to the requirement keyword may be represented by using an "@ [" symbol as the beginning and an "]" symbol as the end.
For the above step S201, in a specific implementation, for each requirement keyword, the keyword identifier corresponding to the requirement keyword is determined according to the category information of the requirement keyword. Continuing with the embodiment in step S101, when the requirement keyword is "customer" or "sales", it is determined that the category information of the requirement keyword is a user keyword, and thus the keyword identifier corresponding to the requirement keyword is a user keyword identifier; when the requirement keyword is 'present or absent' or 'absent', determining that the category information of the requirement keyword is a single keyword, and thus a keyword identifier corresponding to the requirement keyword is a single keyword identifier; when the requirement keyword is 'medicine', the category information of the requirement keyword is determined to be a composite keyword, and therefore the keyword identifier corresponding to the requirement keyword is a composite keyword identifier.
Here, it should be noted that the above examples of the category information of the requirement keyword and the keyword identifier corresponding to the requirement keyword are merely examples, and actually, the category information of the requirement keyword and the keyword identifier corresponding to the requirement keyword are not limited to the above examples.
S202, adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword.
It should be noted that the keyword rule refers to a rule for detecting whether the session data to be matched contains the keyword.
In step S202, a corresponding keyword identifier is determined for each required keyword, and the required keyword is added to the keyword identifier to generate a keyword rule of the required keyword. Continuing the embodiment in step S201, when the requirement keyword is "client", adding the requirement keyword to the user keyword identifier, and the generated keyword rule is "@ [ client ]"; when the requirement keyword is 'sale', adding the requirement keyword into the user keyword identification, wherein the generated keyword rule is '@ [ sale ]'; when the requirement keyword is 'presence or absence', adding the requirement keyword into the single keyword identifier, and generating a keyword rule of 'presence or absence'; when the requirement keyword is 'none', adding the requirement keyword into the single keyword identifier, and generating a keyword rule of 'none'; when the requirement keyword is "medicine", the requirement keyword is added to the user keyword identification, and the generated keyword rule is "< medicine >.
Here, it should be noted that the above examples of the keyword rule for the requirement keyword are merely examples, and in practice, the keyword rule for the requirement keyword is not limited to the above examples.
S203, based on the service detection requirement, determining a logic operator of the keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection.
It should be noted that the logical operator refers to a common set of operation symbols for performing a logical operation, and is used for combining the keyword rules of two adjacent requirement keywords. The session detection number refers to session detection data required for detecting session data to be matched, for example, the session detection number may be 5 or 20, and this application is not limited in particular.
In particular, the logical operators may include "and" ("&"), "or" ("|"), "not" ("|). For example, when the business detection requirement is to detect whether a customer mentions a medicine, the requirement keywords determined according to the business detection requirement are "customer" and "medicine", and the determined logical operator should be "and", which means that the session data to be matched is both sent by the customer and contains the composite keyword of "medicine". When the business detection requirement is to detect whether medicines or foods are mentioned, the requirement keywords determined according to the business detection requirement are medicines and foods, and the determined logical operator is 'OR', which means that the session data to be matched can be a compound keyword containing medicines or a compound keyword containing foods. When the business detection requirement is to detect whether the medicine is not mentioned, the determined logical operator should be 'not', which means that the session data to be matched does not contain the compound keyword of 'medicine'.
Here, it should be noted that the above examples of the logical operator are merely examples, and in practice, the logical operator is not limited to the above examples.
With respect to the step S203, at least one logical operator and the number of session detections required for detection are determined based on the service detection requirement. Continuing with the embodiment in step S202, continuing with the embodiment in step S203, when the service detection requirement is "sales service violation", the determined logical operator should be and "because the service violation requires the client to mention" presence or absence "in one piece of session data to be matched and the sales to mention" absence "in another piece of session data to be matched, so the logical operator combining the keyword rules of" client "and" presence or absence "should be and, symbolically denoted as" & ", and the logical operator combining the keyword rules of" sales "and" absence "should be and, symbolically denoted as" & ". The number of session detections determined to be required for detecting each session data to be matched may be 5. When the service detection requirement is ' whether the client is interested in the medicine ', the determined logical operator should be ' and ', because the client's interest in the medicine requires the client to simultaneously refer to the compound keyword and ' presence or absence ' of the ' medicine ' in a piece of session data to be matched, so the logical operator combining the keyword rules of the two adjacent requirement keywords ' client ' and ' presence or absence ' should be ' and ', symbolically indicated as ' & ', and the logical operator combining the keyword rules of the two adjacent requirement keywords ' presence or absence ' and ' medicine ' should be ' and ', symbolically indicated as ' & '. The number of session detections determined to be required for detecting each session data to be matched may be 2.
S204, combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
In step S204, after the logical operator, the keyword rule, and the number of detected sessions are determined, the logical operator is used to combine the keyword rule and the number of detected sessions of two adjacent required keywords, so as to generate a detection rule for analyzing the detection target indicated by the service detection requirement. For example, when the logical operator is "and", the expression form of the detection rule spliced by the logical operator may be "[ @ [ tensor ] & < food > ] ] [ @ [ sales ] & [ no ] ] ]", which indicates that the session data to be matched is issued by tensor and a composite keyword of "food" is mentioned in the session data to be matched, but the next session data to be matched is issued by "sales" and a "no" keyword is mentioned in the session data to be matched. When the number of session detections is 20, the presentation form of the detection rule may be "[ [ [ welcome ] ] ] [ ] ] {0,20} [ [ bye ] ] ]", which indicates that a plurality of pieces of session data to be matched are matched, starting with a "welcome" keyword, including any session data to be matched from 0 to 20 sentences in the middle, and ending with a "bye" keyword. Wherein "[ ] ]" indicates that arbitrary session data to be matched is matched. In the embodiment continuing the step S203, when the service detection requirement is "whether the service for sale is illegal", the finally obtained detection rule may be expressed as "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,5} [ @ [ sales ] & [ absence ] ] ] ] ]", and when the service detection requirement is "whether the client is interested in the medicine", the finally obtained detection rule may be expressed as "[ @ [ client ] & [ presence or absence ] ] ] ] ] [ ] ] {0,2} [ @ [ client ] & [ medicine ] ] ]".
Here, it should be noted that the expression of the detection rule described above is merely an example, and in practice, the expression of the detection rule is not limited to the above example.
According to the determination method of the detection rule, the used detection rule can detect single session data to be matched, multiple pieces of session data to be matched and session data to be matched based on the context relationship, and the detection rule has the advantages of less identification types, high universality and high cohesion. Meanwhile, the detection rule is based on understanding and abstraction of the service detection requirement, so that the readability and the writeability are high when the detection rule is written.
And S103, determining a session data group to be matched corresponding to each piece of session data to be matched according to the detection rule.
The session data group to be matched comprises the session data to be matched and reference session data having a contextual relation with the session data to be matched.
It should be noted that the session data set to be matched refers to a candidate session data set for determining the target session data set, and as an alternative implementation, the session data set to be matched includes the matching session data and reference session data having a contextual relationship with the session data to be matched. Here, the context refers to an association between two adjacent pieces of session data to be matched. The reference session data refers to session data which is adjacent to the session data to be matched and used for judging whether the session data group to be matched meets the service detection requirement.
For the above step S103, in a specific implementation, for each piece of session data to be matched, according to the detection rule determined in step S102, a session data group to be matched corresponding to the matching session data is determined. As an optional implementation manner, the determining, for each piece of session data to be matched, a session data group to be matched corresponding to the session data to be matched according to the detection rule includes:
step 1031, for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship.
For the above step 1031, in a specific implementation, for each piece of session data to be matched, the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the contextual relationship between the session data are determined according to the session detection quantity in the detection rule determined in step S102. For example, in continuation of the embodiment in step S204, when the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,5} [ @ [ sales ] & [ absence ] ] ]", it is determined that the number of pieces of session data in the session data group to be matched is 5, and the context relationship between the pieces of session data is the following relationship. When the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,2} [ @ [ client ] & [ drug ] ] ]", it is determined that the number of pieces of session data in the session data group to be matched is 2, and the context relationship among the pieces of session data is the following relationship.
Step 1032, the session data to be matched is detected for the first time by using a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined.
It should be noted that the first detection sub-rule refers to a first sub-rule in the detection rules. For example, when the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,5} [ @ [ sales ] & [ absence ] ] ]", the first detection sub-rule is "[ @ [ client ] & [ presence or absence ]", and the sub-detection result is the detection result corresponding to each keyword rule in the first detection sub-rule. The same applies in the case where the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,2} [ @ [ client ] & [ drug ] ] ]", and will not be described again.
For step 1032, each piece of session data to be matched is primarily detected by using a first detection sub-rule in the detection rules, and a sub-detection result of each keyword rule is determined. The sub-detection results include compliance with the keyword rules and non-compliance with the keyword rules. Exemplarily, when the keyword rule is @ [ client ], when a certain piece of session data to be matched is sent by the client, the session data to be matched is considered to conform to the keyword rule; and when a certain piece of session data to be matched is not sent by the client, the session data to be matched is considered to be not in accordance with the keyword rule.
And 1033, performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions.
It should be noted that the secondary detection condition refers to whether the first detection sub-rule is satisfied. With respect to step 1033, after the sub-detection result of each keyword rule in the first detection sub-rule is determined, the logic operator between two adjacent keyword rules is used to perform logic operation on the sub-detection result of each keyword rule, and it is determined whether the session data to be matched meets the secondary detection condition. How to perform the logical operation on the sub-detection result by using the logical operator is described in detail in the prior art, and is not described herein again. After the logical operation is carried out, whether the logical operation result meets the secondary detection condition or not is determined, namely whether the first detection sub-rule is met or not is determined.
And 1034, if yes, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity.
As for the above step 1034, when the session data to be matched satisfies the secondary detection condition, at least one piece of reference session data corresponding to the contextual relationship and the data quantity is extracted from at least one piece of session data to be matched by using the determined contextual relationship and data quantity. In the embodiment in the continuation step 1031, when the number of the determined data is 5 and the contextual relationship between the pieces of session data is the following relationship, 5 pieces of reference session data that are adjacent to the piece of session data to be matched and appear below the piece of session data to be matched are extracted starting from the piece of session data to be matched that satisfies the secondary detection condition.
Step 1035, determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
For the above step 1035, after the session data to be matched and the at least one piece of reference session data are determined, the session data to be matched and the at least one piece of reference session data are combined into one data group as the session data group to be matched corresponding to the session data to be matched.
S104, according to the detection rule, screening out a target conversation data group from the determined at least one conversation data group to be matched.
It should be noted that the target session data set refers to a data set that matches the service detection requirement. As an optional implementation manner for the step S104, the screening, according to the detection rule, a target session data set that meets the detection target from the at least one determined session data set to be matched includes:
step 1041, for each piece of reference session data in each session data group to be matched, primarily detecting the reference session data by using a second detection sub-rule, and determining a sub-detection result of each keyword rule in the second detection sub-rule.
It should be noted that the second detection sub-rule refers to a second sub-rule in the detection rules. For example, when the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,5} [ @ [ sales ] & [ absence ] ] ]", the second detection sub-rule is "[ @ [ sales ] & [ absence ]", the sub-detection result is the detection result corresponding to each keyword rule in the second detection sub-rule. The same applies in the case where the detection rule is "[ @ [ client ] & [ presence or absence ] ] ] [ ] ] {0,2} [ @ [ client ] & [ drug ] ] ]", and will not be described again. The method how to determine the sub-detection result of each keyword rule in the second detection sub-rule is the same as the method how to determine the sub-detection result of each keyword rule in the first detection sub-rule in step 1032, and details thereof are not repeated herein.
Step 1042, performing logical operation on each sub-detection result according to the logical operator, and determining whether the reference session data meets the secondary detection condition.
Step 1043, if yes, determining the session data group to be matched to which the reference session data belongs as the target session data group.
As to the above step 1042 and step 1043, how to perform logical operation on each sub-detection result according to the logical operator to determine whether the reference session data satisfies the secondary detection condition is the same as how to perform logical operation on each sub-detection result according to the logical operator in step 1033 to determine whether the session data to be matched satisfies the secondary detection condition, which is not described herein again. And when any piece of reference session data in at least one piece of reference session data meets the secondary detection condition, determining the session data group to be matched to which the reference session data belongs as a target session data group.
And S105, determining a service detection result of the service detection requirement in the preset time period based on the number of the target session data groups.
For the above step S105, after the target session data set is determined, according to the number of the target session data sets, a service detection result required for service detection in a preset time period is determined. As an optional implementation manner, the determining, based on the number of the target session data sets, a service detection result of the service detection requirement in the preset time period includes:
step 1051, determining the existence ratio of the session data to be matched which accords with the detection rule in the at least one session data to be matched based on the number of the target session data group and the number of the at least one session data to be matched.
For step 1051, in a specific implementation, the number of target session data groups and the number of at least one piece of session data to be matched related to a service detection requirement in a preset time period are obtained, and the number of the target session data groups and the number of the at least one piece of session data to be matched are divided to obtain a presence ratio of the session data to be matched in the at least one piece of session data to be matched, which meets the detection rule.
Step 1052, determining a service detection result of the service detection requirement in the preset time period based on the existence ratio.
For the above step 1052, in a specific implementation, after the existence proportion is determined, a service detection result of the service detection requirement in a preset time period is determined by using the existence proportion and a preset proportion threshold. For example, the service detection requirement is "whether the sold service is illegal", when the determined existence proportion is greater than or equal to the preset proportion threshold, the service detection result of the service detection requirement is determined to be illegal, and when the determined existence proportion is less than the preset proportion threshold, the service detection result of the service detection requirement is determined to be illegal. For example, the service detection requirement is "whether the customer is interested in the medicine", when the determined presence ratio is greater than or equal to the preset ratio threshold, the service detection result of the service detection requirement is determined to be interested, and when the determined presence ratio is less than the preset ratio threshold, the service detection result of the service detection requirement is determined to be uninterested.
The method for determining the service detection result provided by the embodiment of the application can generate the corresponding detection rule according to the service detection requirement, the used detection rule can detect single session data to be matched, multiple session data to be matched and session data to be matched based on the context relationship, and the detection rule has the advantages of less identification types, high universality and high cohesion. Meanwhile, the detection rule is based on understanding and abstraction of the service detection requirement, so that the readability and the writeability are high when the detection rule is written. Meanwhile, the staff can write the detection rules efficiently, the generation efficiency of the detection rules is improved, and the determination efficiency of the service detection results is further improved.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a device for determining a service detection result according to an embodiment of the present application, and as shown in fig. 3, the determining device 300 includes:
an obtaining module 301, configured to obtain at least one requirement keyword for representing a service detection requirement and at least one piece of session data to be matched, where the session data is related to the service detection requirement within a preset time period;
a detection rule determining module 302, configured to determine, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement;
a to-be-matched session data set determining module 303, configured to determine, according to the detection rule, a to-be-matched session data set corresponding to each piece of to-be-matched session data, where the to-be-matched session data set includes the to-be-matched session data and reference session data having a contextual relationship with the to-be-matched session data;
a target session data group determining module 304, configured to screen a target session data group from the determined at least one session data group to be matched according to the detection rule;
a service detection result determining module 305, configured to determine a service detection result of the service detection requirement in the preset time period based on the number of the target session data sets.
Further, when the detection rule determining module 302 is configured to determine, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement, the detection rule determining module 302 is configured to:
determining a keyword identifier corresponding to each demand keyword, wherein the keyword identifier represents category information of the demand keyword;
adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword;
determining a logic operator of a keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection based on the service detection requirement;
and combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
Further, when the to-be-matched session data group 303 determining module is configured to determine, for each to-be-matched session data, a to-be-matched session data group corresponding to the to-be-matched session data according to the detection rule, the to-be-matched session data group determining module 303 is configured to:
for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship;
the session data to be matched are detected for the first time by utilizing a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions;
if so, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity;
and determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
Further, when the target session data group determining module 304 selects, according to the detection rule, a target session data group that meets the detection target from the at least one determined session data group to be matched, the target session data group determining module 304 is configured to:
aiming at each piece of reference session data in each session data group to be matched, primarily detecting the reference session data by using a second detection sub-rule, and determining a sub-detection result of each keyword rule in the second detection sub-rule;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the reference session data meets secondary detection conditions;
and if so, determining the session data group to be matched to which the reference session data belongs as the target session data group.
Further, when the service detection result determining module 305 is configured to determine the service detection result of the service detection requirement in the preset time period based on the number of the target session data sets, the service detection result determining module 305 is configured to:
determining the existence proportion of the session data to be matched which accords with the detection rule in the at least one piece of session data to be matched based on the number of the target session data group and the number of the at least one piece of session data to be matched;
and determining a service detection result of the service detection requirement in the preset time period based on the existence ratio.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 4, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.
The memory 420 stores machine-readable instructions executable by the processor 410, when the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430, and when the machine-readable instructions are executed by the processor 410, the steps of the method for determining a service detection result in the method embodiments shown in fig. 1 and fig. 2 may be performed, so that a problem that session data having a context relationship cannot be detected in the prior art is solved.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the step of the method for determining a service detection result in the method embodiments shown in fig. 1 and fig. 2 may be executed, so as to solve a problem that session data having a context relationship cannot be detected in the prior art.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and 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 of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present application, and are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. A method for determining a service detection result is characterized in that the method for determining comprises the following steps:
acquiring at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched, which is related to the service detection requirement in a preset time period;
determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword;
for each piece of session data to be matched, determining a session data group to be matched corresponding to the session data to be matched according to the detection rule, wherein the session data group to be matched comprises the session data to be matched and reference session data having a context relationship with the session data to be matched;
screening a target conversation data group from the determined at least one conversation data group to be matched according to the detection rule;
determining a service detection result of the service detection requirement in the preset time period based on the number of the target session data groups;
the determining, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement includes:
determining a keyword identifier corresponding to each requirement keyword, wherein the keyword identifier represents category information of the requirement keyword, the keyword identifier refers to an identifier used for constructing the detection rule, and the requirement keyword comprises a single keyword, a composite keyword and a user keyword;
adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword;
determining a logic operator of a keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection based on the service detection requirement;
and combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
2. The determination method according to claim 1, wherein the determining, for each piece of session data to be matched, a session data group to be matched to which the piece of session data to be matched corresponds according to the detection rule includes:
for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship;
the session data to be matched are detected for the first time by utilizing a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions;
if so, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity;
and determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
3. The determination method according to claim 2, wherein the step of screening out a target session data set which meets the detection target from the determined at least one session data set to be matched according to the detection rule comprises;
aiming at each piece of reference session data in each session data group to be matched, primarily detecting the reference session data by using a second detection sub-rule, and determining a sub-detection result of each keyword rule in the second detection sub-rule;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the reference session data meets secondary detection conditions;
and if so, determining the session data group to be matched to which the reference session data belongs as the target session data group.
4. The method according to claim 1, wherein the determining the traffic detection result of the traffic detection requirement in the preset time period based on the number of the target session data groups comprises:
determining the existence proportion of the session data to be matched which accords with the detection rule in the at least one piece of session data to be matched based on the number of the target session data group and the number of the at least one piece of session data to be matched;
and determining a service detection result of the service detection requirement in the preset time period based on the existence ratio.
5. An apparatus for determining a service detection result, the apparatus comprising:
the system comprises an acquisition module, a matching module and a matching module, wherein the acquisition module is used for acquiring at least one requirement keyword for representing service detection requirement and at least one piece of session data to be matched, which is related to the service detection requirement in a preset time period;
the detection rule determining module is used for determining a detection rule for analyzing a detection target indicated by the service detection requirement according to the at least one requirement keyword;
the to-be-matched session data set determining module is used for determining a to-be-matched session data set corresponding to each piece of to-be-matched session data according to the detection rule, wherein the to-be-matched session data set comprises the to-be-matched session data and reference session data having a contextual relation with the to-be-matched session data;
the target session data set determining module is used for screening out a target session data set from the determined at least one session data set to be matched according to the detection rule;
a service detection result determining module, configured to determine a service detection result of the service detection requirement in the preset time period based on the number of the target session data sets;
when the detection rule determining module is configured to determine, according to the at least one requirement keyword, a detection rule for analyzing a detection target indicated by the service detection requirement, the detection rule determining module is configured to:
determining a keyword identifier corresponding to each requirement keyword, wherein the keyword identifier represents category information of the requirement keyword, the keyword identifier refers to an identifier used for constructing the detection rule, and the requirement keyword comprises a single keyword, a composite keyword and a user keyword;
adding the requirement keyword into the keyword identification to generate a keyword rule of the requirement keyword;
determining a logic operator of a keyword rule for combining two adjacent requirement keywords and the number of session detection required by each session data to be matched during detection based on the service detection requirement;
and combining the keyword rule of each required keyword and the session detection number through the logic operator to obtain the detection rule.
6. The apparatus according to claim 5, wherein when the to-be-matched session data group determining module is configured to determine, for each piece of to-be-matched session data, a to-be-matched session data group corresponding to the to-be-matched session data according to the detection rule, the to-be-matched session data group determining module is configured to:
for each piece of session data to be matched, determining the data quantity of the session data in the session data group to be matched to which the session data to be matched belongs and the context relationship among the session data according to the detection rule, wherein the context relationship is an upper context relationship or a lower context relationship;
the session data to be matched are detected for the first time by utilizing a first detection sub-rule, and a sub-detection result of each keyword rule in the first detection sub-rule is determined;
performing logical operation on each sub-detection result according to the logical operator, and determining whether the session data to be matched meets secondary detection conditions;
if so, extracting at least one piece of reference session data from at least one piece of session data to be matched according to the context relationship and the data quantity;
and determining a session data group to be matched corresponding to the session data to be matched based on the session data to be matched and at least one piece of reference session data.
7. An electronic device, comprising: processor, memory and bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions being executed by the processor to perform the steps of the method for determining a traffic detection result according to any of claims 1 to 4.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, performs the steps of the method for determining a traffic detection result according to any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111416742.9A CN113836288B (en) | 2021-11-26 | 2021-11-26 | Method and device for determining service detection result and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111416742.9A CN113836288B (en) | 2021-11-26 | 2021-11-26 | Method and device for determining service detection result and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113836288A CN113836288A (en) | 2021-12-24 |
CN113836288B true CN113836288B (en) | 2022-03-29 |
Family
ID=78971479
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111416742.9A Active CN113836288B (en) | 2021-11-26 | 2021-11-26 | Method and device for determining service detection result and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113836288B (en) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150363791A1 (en) * | 2014-01-10 | 2015-12-17 | Hybrid Application Security Ltd. | Business action based fraud detection system and method |
CN108962282B (en) * | 2018-06-19 | 2021-07-13 | 京北方信息技术股份有限公司 | Voice detection analysis method and device, computer equipment and storage medium |
CN111984779B (en) * | 2020-09-10 | 2024-05-28 | 支付宝(杭州)信息技术有限公司 | Dialogue text analysis method, device, equipment and readable medium |
CN112528017A (en) * | 2020-11-30 | 2021-03-19 | 北京搜狗科技发展有限公司 | Automatic conversation flow analysis method and device |
-
2021
- 2021-11-26 CN CN202111416742.9A patent/CN113836288B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113836288A (en) | 2021-12-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107784051B (en) | Online customer service response system and method | |
US9965443B2 (en) | Method for determining a sentiment from a text | |
US20160019885A1 (en) | Word cloud display | |
US20140365461A1 (en) | Customer support solution recommendation system | |
US10860566B1 (en) | Themes surfacing for communication data analysis | |
CN105359181A (en) | Assessing value of brand based on online content | |
CN113379398B (en) | Project requirement generation method and device, electronic equipment and storage medium | |
EP3031030A1 (en) | Methods and apparatus for determining outcomes of on-line conversations and similar discourses through analysis of expressions of sentiment during the conversations | |
CN112559903A (en) | Community member searching method, system, device and medium | |
US10395270B2 (en) | System and method for recommending a grammar for a message campaign used by a message optimization system | |
CN113705250B (en) | Session content identification method, device, equipment and computer readable medium | |
Rizun et al. | Discovery of stylistic patterns in business process textual descriptions: It ticket case | |
Modaresi et al. | On (commercial) benefits of automatic text summarization systems in the news domain: a case of media monitoring and media response analysis | |
CN114676231A (en) | Target information detection method, device and medium | |
JP2017091376A (en) | Advertisement system and advertisement delivery method | |
CN113836288B (en) | Method and device for determining service detection result and electronic equipment | |
JP2016184330A (en) | Approach support system, Approach support method and Approach support program | |
US20220043849A1 (en) | Document processing program and information processing apparatus | |
CN113791860B (en) | Information conversion method, device and storage medium | |
Beaver et al. | Towards awareness of human relational strategies in virtual agents | |
CN115564529A (en) | Voice navigation control method and device, computer terminal and storage medium | |
KR102078541B1 (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same | |
CN113191777A (en) | Risk identification method and device | |
JP5702753B2 (en) | Event detection apparatus, method, and program | |
JP6525051B2 (en) | Text monitoring system, text monitoring method, and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |