Content analysis method, system and equipment based on dissimilatory regularization and medium

Abstract

The invention relates to a dissimilatory regularization-based content analysis method, a dissimilatory regularization-based content analysis system, dissimilatory regularization-based content analysis equipment and a medium. Performing rule configuration by using a pre-designed dissimilatory regular expression, wherein the dissimilatory regular expression comprises keywords and relational symbols for connecting the keywords; and analyzing the to-be-analyzed text content by using the configured rule to obtain an analysis result. Compared with the prior art, the method has the advantages of being capable of comprehensively and accurately analyzing text content, extracting needed elements and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of text analysis, and in particular to a content analysis method, system, device and medium based on alienation regularization. Background Art

[0002] In the existing field of conference quality detection, existing technical means mainly include manual review and simple text keyword matching. Manual review requires a lot of manpower and time costs, and the review results are easily affected by the subjective factors of the reviewers, lacking objectivity and consistency. In addition, manual review is inefficient and difficult to cope with a large number of meetings. Although simple text keyword matching technology can improve detection efficiency to a certain extent, it has the problem of low accuracy. This technology can only identify fixed keywords, and it is difficult to handle keyword deformation, synonyms or context changes, and cannot meet the detection needs of complex conference content.

[0003] For example, in the field of quality inspection of insurance agent meetings, existing technologies may not be able to accurately identify different statements such as "Today's participants are..." and "Today's meeting is...", resulting in missed inspections. In terms of performance reporting, existing technologies may not be able to accurately extract various performance data, such as "This week's performance insurance policies are XX pieces, with a standard insurance amount of XX million", and are prone to errors or omissions. In terms of activity volume reporting, KYC analysis, and review summaries, existing technologies are also difficult to conduct comprehensive and accurate inspections. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a content analysis method, system, device and medium based on alienation regularization.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] According to a first aspect of the present invention, a content analysis method based on alienation regularization is provided, the method comprising the following steps:

[0007] Get the text content to be analyzed;

[0008] Using a pre-designed alienated regular expression to configure rules, the alienated regular expression includes keywords and relationship symbols for connecting keywords;

[0009] Use the configured rules to analyze the text content to obtain the analysis results.

[0010] As a preferred technical solution, the relational symbols include the relational symbol "&" representing the AND relationship, the relational symbol "|" representing the OR relationship, the relational symbol "!" representing the NOT operation, the relational symbol "^" representing NOT a certain keyword, the relational symbol "#" representing proximity, the relational symbol "@" representing character count limit, and the relational symbols ">" and "<" representing the order of words. Among them, @N means that the character count between two groups of words before and after is not more than N, a>b means that word a comes before word b, and a<b means that word a comes after word b.

[0011] As a preferred technical solution, the method is used for the analysis of the content of insurance agent meetings, including the content analysis of the performance report part, the activity volume review part, and the KYC (Know Your Customer) analysis part. The quality inspection analysis of the meeting content is realized through the regular polling of the meeting content, and the score calculation of the result items is carried out according to the business rules. At the same time, the meeting number, the quality inspection result items, and the scores are saved.

[0012] As a preferred technical solution, for the performance report part, for the notification to participants, the configuration rule ((today|今日)>(参会|与会|出席)>(负责人|总|经理|伙伴|主管|团队长|内勤|中支|团险部|团选部|中资)) is used to detect the participation status of personnel in different positions; for the performance report, the configuration rule (short-term insurance>effective>ten thousand) is used to extract performance data; for the activity volume report, the configuration rule ((看|通报|回顾)>(周|月|星期|礼拜)>(活动量|合作量|活动率|转化率|打卡|日志)@N)|((活动量|合作量)>做>(通报|回顾)) is used to identify the content of the activity volume report.

[0013] As a preferred technical solution, for the activity volume review part, for the situation report of the business department, the configuration rule ((最近|周|天|星期|礼拜)>(复盘|高客活动|合计|缺)>场) is used to detect the review situation of the business department. For the business summary, the configuration rule ((客户|她)>(买|成交)>(原因|理由))|((他|客户)>(成交|出单|落单)>原因) is used to analyze the reasons for customer transactions.

[0014] As a preferred technical solution, in the KYC analysis part, for basic information, the rule ((customer|he)>(age|age)>years old) is configured to extract customer age information; for demand analysis, the rule ((care|worry|focus)>(point|key|place)>which@N) is configured to analyze customer concerns; for protection plan, the rule (protection>plan>(aspect|if|is)) is configured to identify the content of the protection plan; for matters to be promoted this week, the rule (promotion>matter>is) is configured to identify matters to be promoted this week; for subsequent actions, the rule ((subsequent|next|after)>(action|plan|intention)) is configured to identify subsequent arrangements; for specific visit plans, the rule (specific>visit>(plan|planning|intention|plan)) is configured to identify subsequent visit plans.

[0015] As a preferred technical solution, the text content to be analyzed is obtained by performing speech recognition conversion based on the audio recording.

[0016] According to a second aspect of the present invention, a content analysis system based on alienation regularization is provided for implementing the method described, the system comprising:

[0017] An analysis content acquisition module is used to acquire the text content to be analyzed;

[0018] A rule configuration module, used for configuring rules using a pre-designed alienated regular expression, wherein the alienated regular expression includes keywords and relationship symbols for connecting the keywords;

[0019] The result output module is used to analyze the text content to be analyzed using the configured rules to obtain the analysis results.

[0020] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the method described above is implemented when the processor executes the program.

[0021] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described when executed by a processor.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] (1) The present invention introduces alienated regular expressions, which greatly improves the flexibility and accuracy of detection. Compared with the prior art that can only identify fixed keywords, alienated regular expressions can handle various changes in keywords and complex contextual relationships, greatly improving the detection accuracy and reducing misjudgments and omissions.

[0024] (2) The present invention sets detailed rules for specific business content of insurance agent meetings, covering multiple key links such as performance reporting, activity review, KYC analysis and review summary, making the detection more targeted. For example, various data can be accurately extracted from performance reports to provide a reliable basis for business decision-making.

[0025] (3) In terms of efficiency, the present invention can automatically perform content analysis according to set rules. The automated process reduces the workload of manual review and improves quality inspection efficiency.

[0026] (4) The present invention can quickly feedback analysis results, calculate scores and execute business rules in a timely manner, and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0030] This embodiment takes the quality inspection of insurance agent meetings as an implementation object and is described in detail as follows. First, a content analysis method based on alienation regularization is provided, such as Figure 1 As shown, the method comprises the following steps:

[0031] S1, obtain the text content to be analyzed.

[0032] In this embodiment, the insurance agent makes an appointment for a DingTalk meeting through the business system, and the DingTalk meeting platform records the meeting recording and converts it into text. When content analysis is required, the meeting text is obtained from the DingTalk platform according to the meeting number.

[0033] S2, perform rule configuration using a pre-designed dissimilation regular expression, where the dissimilation regular expression includes keywords and relational operators for connecting the keywords.

[0034] In this embodiment, the relational operators include the relational operator "&" representing the AND relationship, the relational operator "|" representing the OR relationship, the relational operator "!" representing the NOT operation, the relational operator "^" representing NOT a certain keyword, the relational operator "#" representing the proximity relationship, the relational operator "@" representing the character count limit, and the relational operators ">" and "<" representing the word order. Among them, @N means that the character count between two groups of words before and after is not more than N, a>b means that word a is before word b, and a<b means that word a is after word b.

[0035] Based on the application scenario of insurance agent meeting content analysis, it includes content analysis of the performance report part, the activity volume review part, and the KYC (Know Your Customer) analysis part.

[0036] In the performance report part, for the notification to participants, configure the rule ((today|今日)>(参会|与会|出席)>(负责人|总|经理|伙伴|主管|团队长|内勤|中支|团险部|团选部|中资)) to detect the participation of personnel in different positions; for the performance report, configure the rule (短险>生效>万) to extract performance data; for the activity volume report, configure the rule ((看|通报|回顾)>(周|月|星期|礼拜)>(活动量|合作量|活动率|转化率|打卡|日志)@15)|((活动量|合作量)>做>(通报|回顾)) to identify the content of the activity volume report. Among them, @15 means that the character count between the two groups of keywords (周|月|星期|礼拜) and (活动量|合作量|活动率|转化率|打卡|日志) is not more than 15.

[0037] In the activity volume review part, for the situation report of the business department, configure the rule ((最近|周|天|星期|礼拜)>(复盘|高客活动|合计|缺)>场) to detect the review situation of the business department, and for the business summary, configure the rule ((客户|她)>(买|成交)>(原因|理由))|((他|客户)>(成交|出单|落单)>原因) to analyze the reasons for customer transactions.

[0038] In the KYC analysis section, for basic information, configure the rule ((customer|he)>(age|age)>years old) to extract customer age information; for demand analysis, configure the rule ((care|worry|focus)>(point|key|place)>which@15) to analyze customer concerns; for protection plan, configure the rule (protection>plan>(aspect|if|is)) to identify the content of the protection plan; for this week's progress, configure the rule (progress>matter>is) to identify this week's progress; for follow-up actions, configure the rule ((follow-up|next|after)>(action|plan|intention)) to identify follow-up arrangements; for specific visit plans, configure the rule (specific>visit>(plan|planning|intention|plan)) to identify the follow-up visit plan.

[0039] S3: Analyze the text content to be analyzed using the configured rules to obtain the analysis results.

[0040] The business system transfers the obtained DingTalk meeting text files to OSS (object storage service) through batch processing. The meeting quality inspection files will periodically poll OSS to obtain the files to be analyzed and analyze them, and calculate the scores of the result items according to business rules, while saving the meeting number, quality inspection result items and scores. After the quality inspection is completed, an MQ (message queue) message is sent to notify the business system. The business system saves the quality inspection result items and calculates the scores of the result items according to business rules. In addition, the meeting number is reflected in the meeting text file for easy management and traceability.

[0041] This embodiment also provides a content analysis system based on alienation regularization, used to implement the method, the system comprising:

[0042] An analysis content acquisition module is used to acquire the text content to be analyzed;

[0043] A rule configuration module, used for configuring rules using a pre-designed alienated regular expression, wherein the alienated regular expression includes keywords and relationship symbols for connecting the keywords;

[0044] The result output module is used to analyze the text content to be analyzed using the configured rules to obtain the analysis results.

[0045] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0046] The above system realizes efficient integration between the insurance agent business system, DingTalk conference platform and OSS, improves data flow efficiency and reduces manual intervention. Finally, it is clear that the system does not have emotion recognition and voiceprint recognition functions, avoiding unnecessary function expansion, focusing more on the core task of conference quality detection, and improving the practicality of the system.

[0047] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0048] Multiple components in the device are connected to the I / O interface, including: input units, such as keyboards, mice, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunication networks.

[0049] The processing unit performs the various methods and processes described above, such as methods S1 to S3. For example, in some embodiments, methods S1 to S3 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S3 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S1 to S3 in any other appropriate manner (e.g., by means of firmware).

[0050] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0051] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0052] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0053] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A content analysis method based on alienation regularization, characterized in that: The method includes the following steps: Obtain the text content to be analyzed; Perform rule configuration using a pre-designed dissimilation regular expression, where the dissimilation regular expression includes keywords and relational operators for connecting the keywords; Analyze the text content to be analyzed using the configured rules to obtain an analysis result.

2. According to claim 1, a content analysis method based on alienation regularization is characterized in that: The relational operators include the relational operator "&" representing an AND relationship, the relational operator "|" representing an OR relationship, the relational operator "!" representing a NOT operation, the relational operator "^" representing NOT a certain keyword, the relational operator "#" representing a proximity relationship, the relational operator "@" representing a character count limit, and the relational operators ">" and "<" representing the order of word usage. Among them, @N means that the character count between two groups of words before and after is limited to no more than N, a>b means that word a is before word b, and a<b means that word a is after word b.

3. The content analysis method based on alienation regularization according to claim 2 is characterized in that: The method is used for the analysis of the content of insurance agent meetings, including the analysis of the performance report part, the activity volume review part, and the KYC analysis part. The quality inspection analysis of the meeting content is realized through the regular polling of the meeting content, and the scoring of the result items is calculated according to the business rules. At the same time, the meeting number, the quality inspection result items, and the scores are saved.

4. The content analysis method based on alienation regularization according to claim 3 is characterized in that: In the performance report part, for the notification to participants, the rule ((today|今日)>(参会|与会|出席)>(负责人|总|经理|伙伴|主管|团队长|内勤|中支|团险部|团选部|中资)) is configured to detect the participation status of personnel in different positions; for the performance report, the rule (short-term insurance>effective>ten thousand) is configured to extract performance data; for the activity volume report, the rule ((看|通报|回顾)>(周|月|星期|礼拜)>(活动量|合作量|活动率|转化率|打卡|日志)@N)|((活动量|合作量)>做>(通报|回顾)) is configured to identify the content of the activity volume report.

5. The content analysis method based on alienation regularization according to claim 3 is characterized in that: In the activity volume review part, for the situation report of the business department, the rule ((最近|周|天|星期|礼拜)>(复盘|高客活动|合计|缺)>场) is configured to detect the review situation of the business department. For the business summary, the rule ((客户|她)>(买|成交)>(原因|理由))|((他|客户)>(成交|出单|落单)>原因) is configured to analyze the reasons for customer transactions.

6. The content analysis method based on alienation regularization according to claim 3 is characterized in that: In the KYC analysis part, for the basic information, the rule ((客户|他)>(年龄|年纪)>岁) is configured to extract the customer's age information; For the needs analysis, the rule ((关心|担心|关注)>(点|关键|地方)>哪@N) is configured to analyze the customer's concerns; for the protection plan, the rule (保障>方案>(方面|的话|是)) is configured to identify the content of the protection plan; for the matters to be promoted this week, the rule (推进>事项>是) is configured to identify the matters to be promoted this week; for the subsequent actions, the rule ((后续|接下来|之后)>(动作|计划|打算)) is configured to identify the subsequent arrangements; for the specific visit plan, the rule (具体>拜访>(计划|规划|打算|方案)) is configured to identify the subsequent visit plan.

7. The content analysis method based on alienation regularization according to claim 1 is characterized in that: The text content to be analyzed is obtained through speech recognition conversion based on the recording.

8. A content analysis system based on alienation regularization, characterized in that: For implementing the method according to any one of claims 1 to 7, the system comprises: An analysis content acquisition module is used to acquire the text content to be analyzed; A rule configuration module, used for configuring rules using a pre-designed alienated regular expression, wherein the alienated regular expression includes keywords and relationship symbols for connecting the keywords; The result output module is used to analyze the text content to be analyzed using the configured rules to obtain the analysis results.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images