JPS6385934A - Intelligent work station - Google Patents

Abstract

PURPOSE:To select an appropriate agent automatically for an incoming call to an absentee, etc., and to rapidly correspond to a requirement, by storing a bit of information representing correlative relation between information which specify plural individuals respectively, and a bit of information regarding the content of a job, as the relation of the agent, in an information accumulating device (data base). CONSTITUTION:When the incoming call is inputted, an automatic operate function in a control part 2 is operated, and a voice synthesizing part 26 and a speech recognizing part 19 are started up. A callee is found from the telephone voice of a caller by speech recognition (a), and it is decided whether response to a call is possible or not, by the retrieval of an individual schedule (c). When the callee is impossible to respond the incoming call, a bit of information regarding a job (requirement) is extracted from a bit of input voice information (f), and the agent instead of the callee is selected to respond the incoming call. When a selected agent is absent, the agent at the next order is found (n), and a message representing the agency of a call is outputted, and the incoming call is transferred (j).

Description

DETAILED DESCRIPTION OF THE INVENTION OBJECTS OF THE INVENTION (Field of Industrial Application) The present invention relates to an intelligent workstation that allows for example to respond appropriately to incoming telephone calls.

(Prior Art) When an incoming call is received to an absentee person, how to respond to the incoming call is an important issue in smoothing office operations. For example, if there is an incoming call regarding an important matter and the person in charge of the matter is absent, it is necessary to have an appropriate representative respond to the call. In other words, it is necessary to select an appropriate agent according to the situation and respond to the incoming call.

Selection of such an agent is the same even in the case of reception, for example, and it is necessary to select an appropriate person in charge according to the visitor's business and contact that person.

Conventionally, therefore, a representative who can deal with the matter is selected by referring to, for example, an organizational chart or a work assignment table, and the telephone is passed on to or contacted by the representative.

However, in modern society where work is diversifying, it is common for individuals to perform multiple duties and for the division of duties to be complicated.

This makes it difficult to select an appropriate substitute.

Furthermore, even if an agent is selected through such procedures, there may be cases in which he or she is actually unable to respond to the request. In addition, there are many cases where the selected agent is absent.

As a result, problems such as repeated call transfers occur each time, making it difficult to take prompt and appropriate responses.

(Problem to be solved by the invention) As described above, in the past, it was extremely difficult to select an appropriate substitute for an incoming call, etc. to an absentee person, for example, from an organizational chart, etc. .

Moreover, such agent selection work is generally a non-productive chore, and has problems such as interfering with the smooth operation of office operations.

The present invention was made in consideration of these circumstances, and its purpose is to automatically select an appropriate substitute for incoming calls, etc. to absentee persons, and promptly respond to the request. The goal is to create an intelligent workstation that can respond to

[Configuration of the Invention (Means for Solving Problems)] As the concept of the present invention is shown in FIG. For example, when there is an incoming telephone call, the telephone voice given through the telephone is recognized and the information related to the person or business content specified by the input information is stored as a relation of the agent. According to the information, personal schedules and agent relationships stored in the information storage device are searched.

If the person receiving the incoming call is not present, the information of the person (proxy) who can respond to the input is requested from the above database, and the incoming call is transferred to the proxy, etc., to the old telephone. This has been made to correspond.

In particular, prioritize and register multiple agents,
The system quickly searches for an appropriate agent by referring to the personal schedules of agents selected in order of priority.

(Function) Thus, according to the present invention, if the individual specified by the incoming call is absent, an appropriate substitute according to the business is automatically selected by searching the agent relations in the database. The call will then be automatically forwarded to this agent. Therefore, it becomes possible to quickly transfer an incoming call to an appropriate agent, who can deal with the call.

Therefore, there is no need to search through complicated organizational charts, etc., and it is possible to reduce miscellaneous tasks and facilitate office operations.

(Example) Embodiments of the present invention will be described below with reference to the drawings.

FIG. 2 is a schematic diagram of an intelligent workstation according to an embodiment of the present invention. This intelligent workstation
It is composed of the following parts.

Bus 1: Used to transfer necessary information between each section described below.

Control unit 2: Mainly composed of a microprocessor, it controls the operations of each part of the intelligent workstation.

Image input device 3; consists of a camera, scanner, OCR, etc., and inputs various image information.

Position coordinate input device 4; consists of a tablet, mouse, etc.
Enter the specified location coordinate information.

Audio input unit 5: Consists of a microphone, etc., and inputs audio information.

Keyboard section 6: Equipped with a plurality of keys, for inputting character/symbol codes, control codes, etc.

IC car 1 section 7: As described later, an IC card is installed therein, and necessary information is input/output between the IC card and the IC card.

Bus controller 8; controls information transfer between each unit via bus 1.

Audio output unit 9: Consists of a speaker, etc., and outputs audio information.

Display section 10. It consists of a CRT display, liquid crystal display, etc., and displays characters, figures, images, etc.

Image output device 11. It consists of a fax machine, a color printer, etc., and prints out various image information.

Communication devices 12, 13. the workstation and telephone;
Or, it communicates information with other workstations, terminals, etc. installed in remote locations.

Switching device 14: Switches and uses ffl number of communication devices.

Timer part 15: Provides time information and time information to the workstation.

Encryption processing unit 16: Encrypts various information.

Voice verification unit 17: Verifies whether the given voice information is a specific voice or not.

Image verification unit 18: Performs verification processing to determine whether the given image information is a specific image.

Speech recognition unit 19: Recognizes and processes given speech information.

Speech analysis section 20. The voice input from the voice input unit 5 or the like is analyzed by extracting the characteristics of the voice or the like.

Character recognition unit 21: Recognizes character/symbol patterns input from the image input device 3 or the like.

Image recognition unit 23: Recognizes graphic images and the like input from the image input device 3 and the like.

Output format selection unit 24: Selects and controls the format of information output from the workstation.

Work environment data collection unit 25; collects and inputs information such as the functional status of the workstation and the work environment in the office.

Speech synthesis unit 2B: Generates synthesized speech according to processed data.

Image compositing unit 27; performs compositing processing on a plurality of pieces of image information, and executes image editing processing according to processing data.

Graphic composition processing unit 28: Composes various graphics and executes editing processing such as adding and deleting graphics according to processing data.

Audio compression/expansion unit 29: compresses and encodes audio data, and restores and expands compressed audio data.

Image compression/expansion unit 30; compresses and encodes image data, and restores and expands compressed image data.

Signal processing unit 31: Executes a series of signal processing such as encoding and compressing various signal information, restoring and expanding it, and adding necessary information.

The database unit 32 classifies each piece of information into a plurality of relations and stores them as a database. still,
This database is constructed not only as code information but also as images, sounds, etc.

The intelligent workstation according to the present invention is basically configured with each of the above-mentioned parts, and each of the above-mentioned parts effectively utilizes its respective functions to exhibit an intelligent function as a whole. There is.

Next, the IC car 1 section 7, the encryption processing section 18, and the like, which are not common like the keyboard section 5 and the like mentioned above, but exhibit characteristic functions in this intelligent workstation, will be explained in more detail.

First of all, an IC card has a semiconductor circuit such as a microprocessor and a memory circuit built into the card body 7a, which is the size of a business card, for example, as shown in FIG. It is constructed by providing an interface section 7b for connection to the station main body and a display window section 7c.

The display window section 7c is formed by embedding a transparent polarizer, and its position is set so as not to overlap the interface section 7b or the semiconductor circuit. Also, the card body 7a
Only the portion corresponding to the display window 7C may be transparent, or the entire substrate may be transparent.

Specifically, as shown in an exploded perspective view of FIG. 4, the IC card has a pair of cover substrates 7d.

7as These cover substrates 7d and 7e sandwich an embedded substrate 7f, a core sheet material 7g, and a printed circuit board 7h.
It is constructed by integrally bonding them together by thermocompression.

An input/output terminal 71 is provided on the printed circuit board 7h at a position facing the interface portion 7b, and a liquid crystal display device 7j is provided at a position facing the display window portion 7C. Furthermore, a semiconductor integrated circuit 7k is mounted on the printed circuit board 7h.
is provided. Further, the cover substrate 7e is provided with a metal foil 7m for dissipating heat generated in the printed circuit board 7h.

Note that the holes drilled in the cover boards 7d and 7e, the embedded board H, and the coco art material 7g are the printed board 7h.
The semiconductor integrated circuits 7j and the like integrated therein are provided at positions facing each other. The semiconductor integrated circuit 7, etc. are fitted into these holes, and the cover substrate 7d,
An IC card is constructed by laminating and integrating a 7qs embedded board 7f, a core sheet material 7g, and a printed circuit board 7h.

The input/output terminal 71 is exposed through a hole formed in the cover substrate 7d, and constitutes an interface section 7b that is electrically connected to the workstation main body.

The liquid crystal display device 7j has a liquid crystal layer sandwiched between a pair of polyether sulfone film substrates provided with a spacer in between, as shown in FIG. , a transparent conductive film is formed on the inner surface of the film substrate, and a polarizer or a reflector is provided on the lower film substrate. If the liquid crystal display device 7j is constructed using the polyether sulfon film substrate in this way, it is easy to reduce the thickness to 0.8p or less, compared to the case where the liquid crystal display device is constructed using a glass substrate. This allows the IC card itself to be made thinner.

Further, the driving power for this IC card may be supplied from the workstation main body via the interface section 7b, or it may be built into the card. In this case, it may be incorporated as a sheet-like battery using, for example, a polymer film.

The semiconductor integrated circuit 7 includes, for example, a CPU 7p and a PROM 7q which is a data memory, as shown in FIG.
, E2 PROM 7r, and a selection section 78 for these memories.

FROM? (L is a large-capacity nonvolatile memory that cannot be erased or rewritten, and stores the control program for the cptryp and information that should be permanently recorded.
2FROM? r is a rewritable small-capacity nonvolatile memory that stores information that is updated when used, such as information transaction numbers and information serial numbers.

These memories are selectively driven under the control of the selection section 7s and output information to and from the CPU 7p. The CPU 7p executes necessary information processing using these memories, and outputs information from its interface section to the intelligent workstation main body via the terminal section 7I mentioned above.

The IC card unit 7 is equipped with such an IC card and inputs and outputs information to and from the IC card.

Incidentally, it goes without saying that the IC card is not limited to the configuration described above, and it goes without saying that the IC card section 7 can be configured depending on the configuration.

Next, the encryption processing unit L6 will be explained.

For example, as shown in FIG. 7, the encryption processing unit 16 includes an encryption unit lea, a decryption unit 16b, and a private key file unit le.
e %Public key file part led, and key update part le
It is configured with e.

As the concept is shown in Figure 8, a given original communication text can be encrypted according to an encryption key to generate the encrypted message, or conversely, a given encrypted communication can be decrypted according to the encryption key to generate the encrypted message. Execute the process to obtain the original text.

Private key file part lee and public key file part lad
stores the keys used for this encryption/decryption, and the key update unit lee is in charge of updating these files.

Here, the private key is a key known only to the workstation that owns this encryption processing unit 1B, and is kept secret from other workstations.

On the other hand, public keys are paired with private keys set in each workstation, and are given to other workstations and made public. The public key file section led stores the public keys published by these plurality of workstations in correspondence with each workstation.

As shown in FIG. 9, the encryption unit lea is an RSA processing unit 1.
61 and an encryption type adding unit 18j.

When attempting to encrypt the original communication text and communicate information, the original communication text is encrypted using the public key published by the workstation of the communication partner, and information indicating the type of encryption is added to the encrypted communication text. It creates communication information and communicates it. In addition, the information on the type of encryption is as follows.
For example, it includes information indicating that "0° is not encrypted,""1" indicates that it is encrypted, and information indicating the encryption method.

Further, the decryption unit 16b inputs the encrypted message encrypted and communicated by the workstation using the public key published by the self-workstation, and decrypts it using the private key corresponding to the private key. 10th
As shown in the figure, there is a ciphertext division section teh, a cipher type determination section 16ffi, and a switching section 16n.

lap, and an RSA processing unit IBq.

The ciphertext division section 16 is for dividing the communication information communicated in the above-described format into the above-mentioned cipher type information and the encrypted message, and includes a cipher type determination section 16ff.
i determines whether the message is encrypted based on the encryption type information. If the communication is not encrypted, the communication is outputted via the switching units 16n and 16p, and if it is encrypted, the communication is guided to the R8A processing unit 18q. The encrypted message is decrypted in the RSA processing unit 18q using the private key, and is output via the switching unit tcp.

The R3A processing units IBi, 18Q are configured, for example, as shown in FIG. 11, including a block division unit 18s, an exponentiation/remainder/calculation unit tet, and a block concatenation unit 18u.

Here, the block division section 18s divides the given signal sequence into blocks M1 of a constant length, and the exponentiation/remainder calculation section let divides the given signal sequence into blocks M1.

At each time, a signal sequence N1 of N − M (mod n) is obtained using encrypted ilk. However, n is a fixed value. This signal series N1 is sequentially connected and outputted via the block connection unit 16u.

In the encryption process, the signal sequence M is the original communication text, and the encrypted communication text is obtained from the original communication text as the signal sequence N1. In the decoding process, the signal sequence M1 is an encrypted message, and the original communication text decrypted from this encrypted message is obtained as the signal sequence N1.

The key k responsible for such encryption/decryption is the aforementioned public key and private key, which are set as a pair.

Therefore, each workstation can encrypt communication information according to a public key made public by another workstation, but the encrypted communication can only be decrypted using the secret paired with the public key. Only certain workstations can know the key.

A workstation that wishes to encrypt and communicate information thus encrypts the original communication text in accordance with a public key made public by the workstation with which it communicates.

The communication information can only be decrypted by the communication partner's workstation that has the private key.

Note that it is not necessary to store all the public keys published by other workstations in the public key file led. For example, public keys published by each workstation are stored in a file corresponding to each workstation in a public key file memory provided separately for the system. When information communication becomes necessary, the public key of the communication partner may be read from the public key file memory and stored in the public key file section 16 of the own workstation.

The above is the basic configuration and functions of the encryption processing section 1B.

Next, the image matching section 18 will be explained.

The image matching unit 18 receives image information inputted from the image input device 3, for example, an image of an individual's face, and performs individual identification.

FIG. 12 shows a schematic configuration of this image matching section, in which 18a is an image storage section, 18b is a normalization circuit, and 18a is an image storage section;
c is a binarization (thinning) circuit, and 18d is a feature data extraction circuit. Further, 18c is a data storage section that stores image data, 181' is a search circuit, 18g is a collation circuit, and 18h is an output section.

The image storage section 18a stores image information input through the image input device 3, and performs image verification processing. The normalization circuit 18b performs normalization processing on the image information stored in the image storage section 18a, and the binarization circuit 18c performs binarization processing on the image information.

Specifically, here, the normalization circuit 18b normalizes the size of the individual's face in order to identify the individual based on the image of the individual's face. The binarization circuit 18c performs, for example, edge line detection and thinning processing on the normalized face image to obtain a binary image of the image.

The feature data extraction circuit 18d performs normalization and
This method extracts feature data from binarized image information. That is, in the matching process using a face image, for example, as shown in FIG. 13, the contour of the face is extracted as one feature, and then features such as the eyes, nose, and mouth in that image are also extracted. . Specifically, the contour features of the face are classified as code information, and the distance between the eyes, the size of the mouth (m), the distance between the eyes and the mouth (n), etc. are used as numerical data to create the image. It is extracted as a feature.

Therefore, the data storage unit 18e stores, for example, the 14th facial image feature data obtained for each individual in advance.
It is registered as shown in the figure. That is, the above-mentioned facial image characteristic data is registered for each individual using the individual's name as an identification name, and the facial image data are connected by pointers.

The search circuit 18'' searches the data storage section 18c based on the feature data extracted by the feature data extraction circuit 18d.The search data is then given to the matching circuit 18g, and the feature data extraction circuit 18d searches the data storage section 18c. It is compared with the feature data obtained in .

In this matching process, for example, the feature data of the input image obtained by the feature data extraction circuit 18d is
i is the type of feature), and when the image feature data registered in the data storage unit 18e is Yl, perform the calculation D-Σ IX, -Y, 1, and select the one with the smallest value as a result of the calculation. This is done by identifying the individual as that individual. This identification result is output via the output section 18h.

The image matching unit 18 basically performs matching processing on the input image in this manner, and performs, for example, personal identification of the input image.

Next, the speech recognition section 19 will be explained.

The speech recognition unit 19 is configured as shown in FIG. 15, for example. The audio input circuit L9a inputs the audio signal input from the audio input section 5 or the audio signal received by the communication device 12.13 via the public telephone line, and converts this input audio signal into an appropriate form. Amplifiers that amplify the signal to a certain level, bandpass filters that limit the bandwidth, and A/
It is composed of a D converter and the like. The input audio is limited to signals in a frequency band of, for example, 30 to 3400 Hz, and is quantized into a 12-bit digital signal at a sampling period of 12 KHz in the audio input circuit 19a.

The acoustic processing section 19b is composed of, for example, a product-sum circuit constructed from dedicated hardware. Basically, it operates at high speed in a pipeline manner in synchronization with the audio input circuit 19a.

The acoustic processing here is performed by two types of bandpass filter groups. One of them is a 16-channel filter bank, through which changes in the spectrum of the input audio signal are extracted.

The other is a gloss filter that divides the same band into four channels, and the acoustic features of the input voice are extracted through this gloss filter.

These two types of filter groups (filter bank and gross filter) are configured, for example, as fourth-order cyclic digital filters. And for example 1 Offlsec
The filtering output is obtained each time. Note that this sound processing section is controlled by a microprogram method.

Therefore, the preprocessing/recognition unit 19c is a high-speed processor 19.
d1 pattern matching processing section 19e1, word dictionary memory 19r1, and buffer memory 19g.

The buffer memory 19g inputs the audio signal filtered by the audio processing section 19b, and receives, for example, a maximum of 1
．． It stores 8 seconds worth of audio data. The high-speed processor L9d performs voice section detection, resampling, labeling, recognition processing using a transition network, and comprehensive logical judgment processing on the data stored in the buffer memory 19g. The high-speed processor 19d also performs communication with the host computer and controls the overall operation of the speech recognition section 19.

The pattern matching processing unit 19c performs matching processing such as calculating the degree of similarity between the speech data processed by the high-speed processor 19d and the standard pattern data of the word speech registered in the word dictionary memory 19f. ,
We are looking for recognition candidates.

For example, speech words to be recognized are uttered discretely.

Therefore, the high-speed processor 19d detects the input section of word speech using input speech energy calculated every 10 Illsec during acoustic processing, for example.

Specifically, as shown in FIG. 16, a threshold E is adaptively calculated from the background noise level and the input audio level, and the input audio signal level exceeds the threshold Eo for a certain period of time or more. , the point in time when the threshold value E is exceeded is detected as the starting point S of the spoken word. Thereafter, the level of the input audio signal reaches the threshold E. When the threshold value E is continuously lowered for a certain period of time or more, the point in time when the threshold value E is lowered is detected as the end point E of the spoken word.

By the way, speech recognition can be considered as a type of pattern recognition. However, there are variations in the patterns peculiar to speech, individual differences due to the gender of the speaker, the shape of the vocal organs, the method of enunciation, etc., as well as noise generated by the speaker himself or herself, noise from the surrounding environment, and even, in the case of telephone speech, public noise. There are problems with level differences and noise caused by going through a telephone line. Therefore, the problem is how to accurately and stably recognize speech by taking these into account and absorbing the above-mentioned fluctuating factors.

Therefore, the preprocessing/recognition unit 19c employs a recognition method called a hybrid structure matching method, which combines the pattern matching method and the structural analysis method in two stages.

That is, when a word speech section is detected as described above, the speech section (S, E) is first divided into 15 equal parts, and each of the 16 points is set as a resample point. Then, the spectrum at each resample point is extracted from the 16 channels of audio data (spectral time series) that have been acoustically processed as described above. Note that if there is a deviation between the sample point of the audio data and the resample point, the spectrum of the nearest point to the resample point may be extracted.

Through this sample processing, an 18X1B (-258)-dimensional voice pattern vector X is obtained. That is, the jth
<j-1, 2, 3, ~ 1B)-th resample point is r, then the 18-channel Svek J Cottle data at r is S(,)-(S , S , NS ,) r J
lrko, 2rJ,
16r3, and rearrange these S's to obtain lrl, lr2. 2rl, 16rlB
)LX■ (S S NS N
Find the vector X of the voice pattern S. However, t indicates the transposition of the matrix.

Input speech pattern vector X obtained in this way
The degree of similarity between this word and a standard pattern of word sounds registered in advance in the word dictionary memory 191' is calculated by, for example, a composite similarity method.

Here, the standard pattern of word sounds registered in advance in the word dictionary memory 19f' is (ψ, ψ ~ ψ) 1k 2' Lk (λ λ ~ λ) 1 '2' L for the word category ωk. However, (λ ≧λ ≧~≧λLk) 1k 2 is provided as $. Furthermore, ψ λ is the category, ni'
, the eigenvectors and their eigenvalues in the dispersion matrix K of the pattern vector X belonging to ωk. For such a word dictionary, the above-mentioned degree of similarity S (k) is calculated as follows. Note that in the above equation, II X II is the norm of the vector X.

Such composite similarity calculations are performed for all categories, and the top similarity value and the resulting category name are determined as a pair.

Pattern matching using such a composite similarity method enables recognition processing that eliminates many pattern variations. However, for similar patterns or patterns with added noise, the difference in similarity values between different categories may become small.

Therefore, as mentioned above, the following structural analysis method has been introduced as a supplement to the pattern matching method. This structural analysis performs recognition processing by focusing on the differences in the sounds that make up word speech, and consists of two types: a phoneme label series and an acoustic feature series.
It uses two time series.

That is, the phoneme label sequence is 10m5e from the input audio signal.
The degree of similarity with the phoneme dictionary is calculated using the spectrum of 16 channels calculated for each c, and phonemes having a degree of similarity of a certain value "-" are labeled and determined. Note that this phoneme label consists of six types, for example, five vowels and nasal sounds. At this time, it is preferable to prepare separate phoneme dictionaries for male voices and female voices.

Compared to vowels, which are pronounced relatively stably, it is difficult to label consonants individually as phonemes. Therefore, the consonant is labeled with its acoustic characteristics,
This is taken as characteristic information. Specifically, acoustic features are extracted from the output of a four-channel gross filter and audio energy obtained through acoustic processing. The acoustic features extracted and labeled in this way are, for example, the 17th
As shown in the figure in comparison with the characteristics of the output of the gloss filter, it consists of 12 PIs such as silence, voicelessness, friction, rupture, and energy dip.

Thus, the phoneme/acoustic label sequence obtained for the input speech is as follows over the range including the speech section (S, E):
The information is input to a transition network created for each word category, as shown in FIG. 18, for example.

The presence or absence of the specified phoneme label or acoustic feature is checked for each node of this transition network. Then, if there is no one, reject it, and if there is one, move to the next node,
When the feature sequence ends, the input sequence that has reached the goal of the transition network is accepted, and its category is determined. Note that the direction of sequence checking can be selected from forward to reverse for each network.

The comprehensive judgment logic is a logic that synthesizes the candidate categories ordered by pattern matching as described above and the recognition results obtained by the transition network, and makes a final judgment.

That is, in this comprehensive judgment logic, when the maximum similarity obtained by pattern matching is set to 81, this is compared with a predetermined threshold value θ. In the case of (Sl×θ), this is rejected as noise.

In addition, in the case of (S1≧θ), another threshold value Δθ is used to
Categories with a degree of similarity greater than or equal to Sl−Δθ) are extracted as candidates. If the number n of extracted categories is one, this is extracted as the recognition result. Furthermore, when a plurality of categories are extracted, only the categories accepted by the transition network are extracted by referring to the analysis results by the transition network. Then, the category with the greatest degree of similarity is determined as the recognition result.

Note that if the categories extracted by the threshold processing do not include those accepted by the transition network, determination is not possible.

As described above, the input word speech is recognized by integrating the pattern recognition processing result using the composite similarity method and the recognition result using the transition network.゛Figure 19 shows the flow of the word speech recognition processing procedure in this speech recognition unit. After speech section detection processing, resampling processing and pattern matching are performed, and at the same time, labeling processing is performed and checking is performed using a transition network. It will be shown that after that, these recognition results are integrated and a comprehensive judgment logic process is performed. Such processing is executed under a processing sequence by the high-speed processor 19d.

By the way, if you want to recognize words in continuously uttered speech instead of discretely uttered word sounds, the following may be used. That is, in this case, the input speech may be divided into various sub-intervals, and the word similarity may be determined by performing rIt word identification for each sub-interval.

Specifically, for example, as shown in FIG. 20, all analysis frames in an input speech section are set as boundary candidates for partial sections, and the input speech section is divided into a plurality of subintervals. At this time, since the maximum time length D and the minimum time length D can be set for the duration of the word to be recognized, only a partial interval 1n within the range needs to be targeted for recognition processing.

In the example shown in FIG. 20, two partial sections are calculated assuming that the number of words in the continuously uttered voice is two. However, since the number of words in the input speech is generally unknown, it is sufficient to assume that 2 to n words exist as word candidates and to detect each partial interval. Then, calculate the word similarity for each detected subinterval,
The connections between the similarity results may be compared with each other to find the most reliable boundary of the sub-interval, and then the word recognition results for each of the sub-intervals separated by the boundary may be obtained.

However, when calculating word similarity by obtaining subintervals in this manner, the number of subintervals becomes enormous, which hinders speeding up of processing. Therefore, in practice, in consideration of speeding up the processing, for example, the number of input words is 2 to 5 words, 1
Word duration is 128 to 840 m5ec, word length ratio in one utterance is 2.5 or less, frame period is 16a+sec (1 in 2 with 8IIIScte period)
It is a good idea to detect partial intervals by adding restrictions such as (extracting individual words).

In this way, it becomes possible to effectively recognize each word in continuously uttered speech.

By the way, learning of the dictionary (word dictionary) used for such speech recognition processing is performed as follows.

This learning process is roughly divided into (1) a process for determining the characteristic kernel from the vowel pattern and the consonant pattern, and (2) a process for determining the fixed value and eigenvector for the characteristic kernel. Then, the eigenvalues and eigenvectors are reduced by N in descending order of the values. This process is generally called KL expansion.

First, the process of determining the characteristic kernel will be described. The characteristic kernel of an input speech pattern (learning pattern) is determined as follows, where S is the vertical vector of the learning pattern.

Here, 5-(S S -3)t m 111'a+2' Iln Note that this learning pattern S is given as a 64-dimensional vertical vector in the case of a consonant pattern.

In the case of a vowel pattern, it is given as a 16-dimensional vertical vector.

Therefore, the characteristic kernel is created by multiplying the vertical vector S of m learning patterns by the horizontal vector S obtained by transposing this vertical vector S.
11
Each component of the resulting matrix is averaged over the m learning patterns. Therefore, the number of elements of the characteristic kernel is the square of the number of elements of the vector.

Note that in order to obtain the characteristic kernel K that reflects the pattern distribution of the category through such processing, a sufficient amount of learning patterns are required. For this reason, it is necessary to store a predetermined number of learning patterns in the learning pattern memory in advance.

However, in the case of vowels, it is only necessary to prepare learning patterns with 18 dimensions and at least six categories, but in the case of consonants, there are 101 categories, and it is necessary to obtain 64-dimensional data. For this reason, it is undeniable that a huge amount of memory capacity will be required if the system is left as it is.

Therefore, in order to obtain a characteristic kernel K that reflects the pattern distribution using a small number of learning patterns, we perform the following process of updating the characteristic kernel, and gradually improve the characteristic kernel to reflect the pattern distribution through sequential calculations. Make it.

That is, the arithmetic process '+wSS t n is repeatedly executed on K-. However, W is a weighting coefficient when updating the characteristic kernel. This weighting coefficient W has a positive or negative value, and if it is positive, it increases the similarity of the characteristic kernel matrix to the input pattern, and if it is negative, it decreases the similarity.

Further, '' indicates the characteristic kernel before learning the learning pattern S, and K indicates the characteristic kernel updated by learning the learning pattern S.

After that, for the characteristic kernel obtained in this way,
Processing is performed to obtain the eigenvalues and eigenvectors, and a standard pattern used in the composite similarity calculation described above is created based on the eigenvalues and eigenvectors.

The standard pattern is obtained by performing KL expansion on the characteristic kernel, for example, by performing KL expansion using power east.

Now, the characteristic kernel K has eigenvalues λ, λ2. 〜λ
n, and the corresponding eigenvectors ξ, ξ2. ~ ■ Let us have ξ. In this case, that arbitrary vector U
are the above eigenvectors ξ, ξ2. ~ ξ is a linear combination of U Σ α, ξ.

()　　　l=　t　　I　l It is expressed as At this time, Kξl″″λl　ξI Since the relationship is established, becomes.

Here 1 λ 1 〉 1 λ 1 〉
〉 1 λ 11 2
n[λl/λ1] > 1 (1=2.3
: ~, n), so when S becomes sufficiently large, the second term in the above equation converges to 0.

Therefore, the above formula Ku −αl λ1 ξ1 It can be made into a stone statue.

5+1 This shows that the ratio between (K u ) and (K u ) is the eigenvalue λl. Also (K
u ) is shown to be proportional to the eigenvector ξl.

By the way, in a calculation process based on such a theory, the results often scale out immediately during the calculation. Therefore, let U be any arbitrary, for example, a unit vector, and vs + l 暉Ku - (V )/(b ) usol sol
The following calculation is executed: sol(s=0.L4...). Here (b)s
ol is the element with the largest absolute value of the vector (V) and so
l Yes. At this time, −(v)/(b) usol sol s+1=(Ku
)/(b) s sol −(Kv)/(b conflict b) s sol sri+1 =(K u )/(b ・・・・・・b )
Since Osol s , from this, λ , b , ξl.

l sol ’ It becomes possible to obtain sol.

Once the eigenvalue λ1 and eigenvector ξ1 with the largest absolute values are determined in this manner, the eigenvalue λ2 and the eigenvector ξ2 with the next highest absolute values are similarly determined.

Now, considering -λ1ξ1ξ1 for K' -, from ξl ξl-0 (l-2, 3, ~, n), for K' ξ - ξ1-λlξ1ξ1 ξ1-λ ξ
−λ1ξ1−0(1−1) to′ ξ −toξ −λ ξ ξ, t ξ1
i lI+ i〜λI ξ1
(i≠1). Therefore, ' in the above becomes 1λ21〉...〉1λr 1〉...〉Iλn 1〉
It can be seen that it has an eigenvalue of 0. It is assumed here that ξl has been normalized.

Such processing is achieved by repeatedly performing the above-mentioned processing on ξ′ obtained by converting the characteristic kernel into ξ′ − as −λ ξ·ξ1 . Through this process, values with large absolute values and their corresponding eigenvectors are determined in order, and dictionary learning is performed.

FIG. 21 shows a dictionary learning process executed based on such a calculation algorithm.

Next, the character recognition section 21 will be explained.

This character recognition unit 21 is composed of a first character recognition block that recognizes characters read by a scanner or the like, and a second character recognition block that recognizes character information input online via a tablet or the like. .

For example, as shown in FIG. 22, this first character recognition block includes an image memory 21a that stores image data read and input by a scanner or the like;
An area detection unit 21b detects an area in which a character to be recognized is written from the image data stored in the image memory 21a, and according to the area detection result, 4 characters to be recognized are detected from the image data stored in the image memory 21a. A character extraction unit 21c that extracts data, and each standard character pattern of recognition target characters registered in advance in the standard pattern dictionary 21d,
It is constituted by an identification section 21c that performs character recognition by individually comparing the character patterns extracted by the character extraction section 21c.

This character recognition block is set at a predetermined position on the FAX transmission manuscript paper 21f' as shown in FIG. 23, for example, and recognizes the characters written in the character frame 21g in which the transmission destination is written. The manuscript paper 211' on which such a transmission destination is written is used as the first manuscript (first sheet) when the transmission manuscript consists of a plurality of sheets. The image data read and input from this first document is stored in the image memory 21a for character recognition processing.

The area detection unit 21b detects the character frame 21 from the predetermined format information of the FAX transmission manuscript paper 21f'.
g position information is obtained, and the area where the character to be recognized is written is detected. The character extraction unit 21c uses this area detection information and the projection pattern information of the image information to individually extract image data of the characters written in the character frame 21g, for example, as shown in FIG. 24. There is.

The identification unit 21e extracts the characteristics of the character pattern from the extracted character image, and registers the extracted character pattern and the standard pattern dictionary 1] 21d, as disclosed in Japanese Patent Publication No. 49-12778, etc. The standard pattern of each character is pattern matched. Then, through this pattern matching, the character category of the standard pattern that has been successfully matched is determined as the recognition result.

It goes without saying that the pattern matching method can be modified in various ways.

By the way, the second character recognition block that recognizes character information input online via a tablet or the like is configured as shown in FIG. 25, for example.

This second character recognition block includes a coordinate detection circuit 21h that sequentially detects a series of positional coordinates indicating each writing stroke of a character input online via a tablet or the like.

The time series data of the position coordinates detected by the coordinate detection circuit 21h is input to the preprocessing circuit 21i, and after removing minute noises such as detection errors in the tablet 4,
The coordinate series storage circuit 21j sequentially stores the coordinates and subjects them to character recognition processing. Note that in this preprocessing circuit 211, for example, 1
When a number of characters are input, the size of the characters is normalized.

Further, the stroke number detection circuit 21 detects the number of writing strokes, that is, the number of strokes, of the character pattern from, for example, breaks in the writing strokes (time-series breaks in the position coordinate data).

Accordingly, the recognition processing unit 21m selectively extracts the standard pattern with the corresponding number of strokes from among the standard patterns of the recognition target character category registered in the standard feature pattern memory 21n according to the information on the number of strokes. The characteristics of each stroke of this standard pattern and the coordinate series storage circuit 21j
The stroke characteristics of the input character pattern stored in the input character pattern are compared with each other (matching process). Answer determination circuit 21
p determines the matching processing result, and obtains a recognition pair type character category having a stroke that corresponds to the stroke characteristics of the input character pattern as the recognition result.

In other words, the input character pattern is recognized by matching the characteristics of the stroke with the stroke characteristics of the standard character pattern according to the characteristics of the writing stroke of the character pattern input online.

Note that information on positional coordinates of end points, intersection points, break points, etc. when a written stroke is approximated by a broken line may be used as the stroke characteristics.

The character recognition unit 21 having the functions described above recognizes character information read and input via a scanner or the like, and character information input online via a position coordinate input device such as a tablet.

Next, the figure recognition section 22 will be explained.

This graphic identification unit 22 is configured as shown in FIG. 26, for example. The input unit 22a stores, for example, a captured and input graphic image, and subjects it to graphic recognition processing.

The contour tracing unit 22b divides the tracing direction of the line segment into eight directions, for example, as shown in FIG. There is. Specifically, for example, as shown in FIG. 28, a triangular figure is tracked clockwise, and information on the tracking direction is stored as, for example, rl, 2. ~2.3,4. ~4.5.7. ~
7" as a series of direction codes.

The segmentation unit 22c extracts singular points, such as curved parts, from the sequence of direction codes obtained in this way, and divides the outline of the figure into a plurality of characteristic parts according to the singular points.

The matching unit 22d performs a matching process on the thus segmented figure contour information and the characteristic information of various figures registered in the dictionary memory 22e, and converts the input figure into 2. It is something that needs to be constructed.

For example, when the figure shown in FIG. 29 is given, three mutually adjacent contour points (1-1), (1),
The sum of the direction codes is calculated in order by (1+1), and this is smoothed as the direction code at the center contour point 1. This smoothing process removes noise components.

Thereafter, the segmentation unit 22c detects end points that are characteristic points of the contour, that is, points where the curve is steep, and divides the contour around the end points.

Then, each divided contour portion is compared with the dictionary memory 22e to obtain the recognition result.

Through the above processing, as shown in Figure 30, a round shape has no end points, a triangular shape has three end points detected, a quadrilateral shape has four end points, etc., so these Each figure is identified and recognized. At this time, information such as that each of the end points is convex or that the contour connecting the end points is a straight line or a curved line may be used for figure identification.

On the other hand, the image recognition section 23 is configured as follows.

FIG. 31 shows a schematic configuration of this image recognition section 23, which includes an original image memory 23a, a binarization device 23b,
It is composed of a processed image memory 23c, a thinning device 23d, and a code conversion device 23o.

The image memory 23a stores a given recognition target image, and the binarization device 23b binarizes it and stores it in the image memory 23c.

This binarization level is variably set, for example, while monitoring the binarized image on a display.

The line thinning device 23d performs line thinning processing on the binarized image and converts the image into a line figure. The image memory 23c is rewritten with the thinned image and subjected to recognition processing.

The code conversion device 23e is configured as shown in FIG. 32, for example, and first divides the thinned image into a plurality of segments in a segment dividing section 231'. This segment division is performed, for example, by dividing the line figure at its end points, branch points, or intersections. Curvature converter 28g
calculates the curvature of each of the segments thus divided.

Straight line/curve dividing section 23h1 curve dividing section 231. The refraction point division section 28j and the inflection point division section 23h further divide each segment divided as described above according to the information on its curvature, and thereby determine the refraction point, the switching point between a straight line and a curved line, Points of inflection, points of radius change in the curve, etc. are detected. Through such segment division and feature point detection, information on each part constituting the image line figure is extracted.

The approximate information creation unit 23■ synthesizes information on these divided segments and feature points in the segments to express the image figure, such as the position coordinates of the starting point and ending point of each segment, and the information on the segment. Obtain code information that identifies the type.

For example, when an input image is given as shown in FIG. 33(a), the image line figure 23n in the input image
is thinned and extracted, and divided into segments as shown in FIG. 3(b). In this example, an image line figure 23n in which a circle figure and a square figure are so-called skewered by straight lines is input. As shown in FIG. 33(b), the image line figure 23n of the lever is divided at the intersection, and segmented into two semicircles, two U-shaped figures, and four straight lines.

The curvature converting section 23g calculates the curvature of each divided segment as shown in FIG. The refraction point dividing section 23j and the inflection point dividing section 23h detect feature points of each segment from the curvature change points. Specifically, in the example shown in FIG. 34(a), the curvature of the two straight lines at the bending point increases sharply, so it is possible to detect the bending point from the change in the curvature. Also, Fig. 34(b)
In the example shown in , since a change in curvature is detected at the transition portion from a straight line to a curve, the feature point can be detected from this change in curvature.

Similarly, in the examples shown in FIGS. 34(c) and 34(d), it is possible to detect the feature point in the segment from the point of change in curvature.

In this manner, the image recognition unit 23 segments the given image figure and detects the feature points of each segment. Then, the image line figure is approximately expressed and recognized as code information indicating each type of a plurality of segments and their position coordinates.

Now, the voice verification section 17 is configured as follows.

This voice matching unit 17 performs individual recognition (
For example, it is configured as shown in FIG. 35.

That is, the speech given through the speech input section 17a is filtered by the phoneme filter 17b and the personal filter 17c, and the speech characteristics are extracted.

Each band of a plurality of channels of the phoneme filter 17b is set by equally dividing the audio frequency band, for example, as shown in FIG. 36(a).

The phonological filter 17b having such filter characteristics extracts feature parameters indicating the phonological characteristics of the input speech. Note that the bandwidth of each channel may be set by dividing the audio frequency band logarithmically.

On the other hand, the bandwidth of each of the plurality of channels of the personal filter 17e is set by exponentially dividing the audio frequency band, as shown in FIG. 36(b). With the personal filter 17e having such filter characteristics, the voice characteristics from the low frequency range to the middle frequency range of the input voice are
This feature is extracted more often than the features on the high frequency side. The filter output of each of these channels is required as a characteristic bug meter for personal verification.

Therefore, the word recognition unit 17d uses the phonological filter 17b.
The word indicated by the input speech is recognized from the phoneme feature parameters obtained through the phonological feature parameter with reference to the word dictionary 17e. This word recognition function is performed by the voice recognition unit 1 mentioned above.
9, and the function of the voice recognition unit 19 may be used as is.

Then, according to the word recognition result, a dictionary to be used for personal verification of the personal dictionary IH is selected. This personal dictionary 17'' is a dictionary in which the results of analysis by the personal filter L7c of specific words uttered in advance by the individual targeted for speaker verification are classified and registered for each word.

The speaker verification unit 17g calculates the degree of similarity between each feature parameter of the corresponding word selected from the personal dictionary 17r and the feature parameter of the input voice found in the personal dictionary 17c, and calculates the degree of similarity. The values are discriminated using predetermined thresholds. Then, by comparing these discrimination results with each other, for example, a personal category with the highest similarity value and a feature parameter with a sufficient difference from the next highest similarity value is determined to be the speaker of the input voice. Personally identified.

Now, to explain in more detail the characteristics of the personal filter 17c, as mentioned above, the phonological feature filter 17b
are set to different characteristics. Considering the distinctiveness of the individuality of this voice, the distinctiveness can be evaluated, for example, by the F ratio given as F ratio - (inter-individual variance)/(intra-individual variance).

Now, phonological filter 17. When considering the F ratio of each channel output with the filter characteristic set to b, an exponential trend is shown by the solid line in FIG.

For this reason, in the past, individual verification has been performed exclusively using voice feature information on the high frequency side.

However, if it is possible to identify individuals using voice features in the entire frequency band, rather than using only high-frequency features of the voice, it is thought that the matching accuracy will be further improved. That is, if the value of the F ratio is 1 or more in all frequency bands and the inter-individual variance exceeds the intra-individual variance, more accurate individual matching becomes possible.

Therefore, here, as mentioned above, the personal filter 17C
The characteristics of the voice are determined exponentially, and the characteristics of the high frequency range where individual characteristics are prominent are roughly extracted, and the audio characteristics of the low frequency range are extracted finely by increasing the number of channels allocated to the low frequency range. That's what I do.

Specifically, since the change in F ratio of each channel shows an exponential tendency, a filter bank in which the bandwidth of the high frequency channel is increased exponentially compared to the bandwidth of the low frequency channel. and configure this as personal filter 17c
It is said that

According to each channel output of the filter 17c configured in this way, the F ratio is as shown by the broken line in FIG. 37, and a significant improvement in the F ratio in the middle range is recognized. As a result, it becomes possible to carry out individual verification by actively utilizing not only the voice characteristics in the high frequency range but also the voice characteristics in the middle frequency range, and it becomes possible to improve the verification accuracy.

That is, in addition to the features used for word recognition of the input speech, the speech matching section 17 uses a filter bank to extract feature information that clearly reveals the individuality of the input speech. As a result, the individual identification of the speaker, that is, the individual verification, is performed with high precision independently of the phoneme recognition of the input speech.

Next, the speech synthesis section 2B will be explained.

The speech synthesis section 26 includes a discriminator 26a as shown in FIG.
, a decoder 26b, a rule parameter generation device 28C2, and a speech synthesizer 26d.

The discriminator 26a determines whether the input code string is a character string or not.
Alternatively, it is determined whether it is a code string indicating an analysis parameter for speech synthesis. This information discrimination is performed, for example, by determining the identification information added at the beginning of the input code string. When it is determined that the code string is an analysis parameter, the code string is given to the decoder 28b, and it is decoded to obtain its phonetic parameters and prosodic parameters.

Further, when it is determined that the character string is a character string, the character string data is provided to the rule synthesis parameter generation device 26c, and is used to generate its phonetic parameters and prosody parameters.

The speech synthesizer 2Bd processes the sound source wave via the vocal tract approximation filter to generate a synthesized speech wave according to the phonological parameters and prosody parameters thus obtained by the decoder 26b or the rule synthesis parameter generation device 26c. is being generated.

To further explain the rule synthesis parameter generation device 28c, the device 28c is configured as shown in FIG. 39. The character string analysis unit 213e identifies each word in the input character string with reference to the language dictionary 26, and obtains grammatical information such as accent information, word/clause boundaries, part of speech, and conjugation for the word.

Then, phonological rules and prosodic rules are applied to the analysis results, and control information thereof is generated.

Here, the phonological rules provide information on the pronunciation of the analyzed words, realize phenomena such as rendaku and devoicing that occur due to word concatenation, and generate the phonological symbol strings.

The speech parameter generation unit 26g inputs this phoneme symbol string, and sequentially obtains syllable parameters from the Cv file 28h in accordance with the syllable unit, and interpolates and combines them. A phonetic parameter sequence is generated from the phonetic symbol string by the phonetic speech parameter generating section 26g.

Prosodic rules determine the boundaries of utterances and breath positions according to grammatical information such as word and clause boundaries, and determine the duration of each sound, pause length, etc.

At the same time, this prosodic rule generates a prosodic symbol string that is based on the basic accent of each word and takes into account the clause accent. The prosodic parameter generation unit 261 inputs this prosodic symbol string and generates a prosodic parameter string representing a temporal change pattern of pitch.

On the other hand, when the input code string is a code string indicating analysis parameters for speech synthesis, the decoder 26b functions as follows.

That is, when the code string of the analysis parameter indicates the cepstral coefficient of the CV file, the code string 26I11 generally corresponds to the parameters P (pitch), C, and C as shown in FIG.
1, to C (cepstral coefficients) Ill are assigned bits and information is compressed.

Therefore, in the decoder 28b, the parameter conversion table 26n
is used to convert and decode the information-compressed analysis parameters into a bit number suitable for the speech synthesizer 26d. For example, each parameter is converted to 8 bits, and a phonological parameter sequence (cepstrum coefficient) and its prosodic parameter sequence (pitch) are determined.

The speech synthesizer 28d includes a voiced sound source 28q and an unvoiced sound source (M-sequence generator) 26', as shown in FIG. 41, for example, and generates a voiced sound source wave (P≠0 ), or silent sound source wave (P-0)
are occurring selectively.

This sound source wave is input to the preamplifier 28s, subjected to signal control according to the cepstrum coefficient C of the phoneme parameter, and input to the logarithmic amplitude approximation digital filter 2Bt. This logarithmic amplitude approximation dicicle filter 26t approximates the vocal tract characteristics according to the cepstrum coefficients C, . This logarithmic amplitude approximation digital filter 28t synthesizes and outputs speech data indicated by the phoneme parameters and prosody parameters.

Then, the signal synthesized by the logarithmic amplitude approximation digital filter 26t is passed through the D/A converter 28u, and then passed through the LPF
26V and output as a synthesized audio signal (analog signal).

In the speech synthesis section 26 configured as shown below, the speech indicated by the input data series is synthesized according to the rules and outputted.

Next, the image composition section 27 will be explained.

As shown in FIG. 42, the image synthesis section 27 includes a control calculation section 27a, a display file memory 27b, two image synthesis circuits C, an image memory 27d, and, if necessary, a display 27e.

Note that this display 27e may be the display unit 10 prepared for the workstation.

The image synthesis circuit 27 reads parameters of vectors, polygons, and arcs written in the display file 27b under the control of a dedicated control calculation unit 27a, generates line figures indicated by the parameters, and synthesizes images. circuit 27
Writing to the specified address of d. The image generation function of the image synthesis circuit 27 constructs a designated line graphic image on the image memory 27d.

This line graphic image is displayed and monitored on the display 27e under the control of the control calculation section 27a.

Further, the image generation circuit 27b has a special processing function for image generation and a filling processing function. This special processing function includes, for example, functions such as removing hidden lines from overlapping image figures and performing clipping processing. The filling function consists of filling a partial area of an image figure with a specified color.

Through the functions of the image synthesis circuit 27b, various image figures are created and their synthesis processing is performed.

By the way, the synthesis of image figures generated as described above and natural pictures can be roughly divided into the following two types. One of them is to use a natural image such as a landscape photograph as a background and perform calculation processing on it.
The other process consists of embedding and synthesizing the obtained images, and the other process consists of embedding and synthesizing a natural image within a planar image that the control calculation unit 27a has as an internal model.

In the case of embedding an image in the former natural image, for example, as shown in FIG. This can be achieved by superimposing this on a natural image and compositing it. Then, in the image area to which the "transparent color" code is given, the information of the natural image is displayed as is, and in the other areas, the figure generated by the control calculation unit 27a is displayed. As a result, image synthesis using a natural image as a background is realized. This technique is called overlay.

On the other hand, as the concept is shown in FIG. 44, a natural image may be written in the image memory, and a figure generated by the control calculation unit 27a may be written on top of it (in the front). . This method is called the two-buffer method,
This can be implemented relatively easily together with the overlay method described above.

By the way, in the latter case, in which a natural image is inserted and synthesized within a plane shown as an internal model of the control calculation unit 27a, high-speed processing is performed as follows.

The coordinate transformation required to embed a natural image on a plane into a plane facing in an arbitrary direction in three-dimensional space is given by the following equation.

However, x and y are the coordinates on the display surface, and u and v are the coordinates on the natural image.

If this coordinate conversion process were to be executed as is, six multiplications and two divisions would be required each time one pixel is displayed, which would require an enormous amount of calculation and calculation processing time.

Therefore, here, the above-mentioned calculation is divided into two conversion processes and executed using the following intermediate coordinates (s, t). This arithmetic processing is executed at high speed using, for example, affine transformation.

u-(α S+α t+α) / t (1)
L 2 3 V-((! s+a8 to 10a9)/15-C3X-C
4Y (2) is CX+C5Y+
C6 In other words, perspective transformation is performed using equation (1) above, and then two-dimensional affine transformation is performed using equation (2) to perform perspective transformation to an arbitrary plane at high speed. There is.

Here, since the denominator of equation (1) is the coordinate t itself, it is convenient to execute the calculation at high speed by just slightly improving the conventionally known affine transformation circuit.

In this way, the image compositing section 27 executes various image compositing processes at high speed.

Next, the output format selection section 24 will be explained.

The output format selection section 24 is activated upon receiving a media selection request signal, and selects which media is to be used to output data. In other words, among various media,
Now is the time to choose which media to use to transmit information.

FIG. 45 is a schematic diagram of the output format selection section 24, in which the media selection control section 24a, the input media determination section 24
b, a partner media determination unit 24C, a media conversion table 24d, and a self-media function table 240. Also, FIG. 46 shows this output format selection section 24.
This shows the flow of processing. The functions of the output format selection section 24 will be explained along the flow of this processing procedure.

When the media selection request signal is given, the media selection control section 24a requests the control section 2 to provide input media information necessary for the media selection operation. Then, it issues a media information detection request and a media function identification request to the input media determining unit 24b.

The input media determining unit 24b is composed of a media detecting unit 24'' and a media identifying unit 24g, and detects the input media given from the control unit 2 in response to an information request from the media selection control unit 24a, and For example, when the input media is audio, the input media determining unit 24b identifies and determines that the function of the media is ADPCM.

Thereafter, the media selection control section 24a informs the control section 2 whether the destination of the data output is another functional block of its own terminal (within the workstation) or another function block connected via a communication line or the like. Determine whether it is a workstation or communication terminal.

When an instruction is given to output data to another workstation or communication terminal, the media selection control unit 2
4a requests the control unit 2 for identification information regarding the destination station. In response to this request, information regarding the partner station that outputs data is input to the partner media determining section 24c.

The partner media determining section 24c is a partner station identifying section 24h.

The partner station media identification unit 2411 is configured to include a function identification unit 24j, and operates upon receiving an identification information determination request from the media selection control unit 24a. Then, first, the partner station is identified from the identification information for the partner station, and the media of the partner station are discriminated. Then, the function of the partner station's media is identified.

Specifically, for example, it is determined that the destination station to which data is to be outputted (transmitted) is an automatic FAX, its communication medium is an image, and its function is Gm type. Note that this identification of the partner station may be performed based on information sent from the partner station using its negotiation (handshake) function. Furthermore, if there is no negotiation function, the function identification section 24j may be provided with the media detection function. In this way, it becomes possible to identify the function according to the media information signal from the other party.

FIG. 47 shows the flow of this partner station identification processing procedure. As shown in this flow, for example, it is determined whether the communication partner station is a telephone or not, and if it is a telephone, it is determined whether or not a FAX signal arrives.

If the other party's station is a telephone and a FAX signal arrives, it is sufficient to identify this as the other party's device being a fax machine. Further, if it is determined that the device is a telephone and no FAX signal arrives, it may be determined that the other party's device is a normal telephone. Further, if it is determined that the device is not a telephone, it may be determined that the other party's device is a communication device other than a telephone.

When the media of the communication partner station is identified in this way, the media selection control unit 24a then refers to the media conversion table 24d configured as shown in FIG. 48, and selects the input media and input function. , obtain media conversion selection information corresponding to the destination device, the destination device media, and the function of the destination device.

For example, if the input media is audio, its function is ADPCM, and the destination device is a GIII type FAX,
It is required that the media of the destination device is an image, and that the main media conversion function is (audio) to (code character) (code character) to (image). At the same time, it is required that the conversion function can be realized by (ADPCM, voice) to (GI[I;FAX). At this time, if dependent media conversion information exists, this information is also obtained at the same time.

The media conversion information obtained in this way is sent to the control unit 2.
and selectively specifying the format of the data output.

In addition, when data output is to be performed inside the own workstation, the media selection control unit 24a refers to the own media function table 24e to find an output format in which the data can be output. According to this information, the media selection control section 24a refers to its own media conversion table of the media conversion table 24d, similarly obtains media conversion information, and provides this to the control section 2.

According to the media conversion information obtained in this way,
For example, the above-mentioned speech synthesis section 26 may be used to convert text information given as a character code series to speech information and output as data, or the speech recognition section I9 may be used to convert speech information to character code series information. The data will be output.

Next, the database section 32 will be explained.

The database unit 32 organizes and stores various data such as codes, images, and sounds, and provides this data to various application systems. Figure 49 shows this database section 3.
2 shows a schematic configuration of an interface section 32a that executes command analysis processing, etc., a data operation section 32b that executes database search processing, etc., a magnetic disk device 32c or an optical disk device as a storage medium for storing various data. 32d1 and its additional function section 320.

Various data are classified and organized into a plurality of relations according to the type of data, and a database is constructed by registering each relation.

The database unit 32 will be explained below by dividing it into four parts: its logical structure, stored data, physical structure, and additional functions.

The logical structure indicates how various data are stored when this database section 32 is viewed from the application system side. Here, data is handled as a logical structure according to the relational model, for example, as a table image as shown in FIG.

A table (relation) has several columns (attributes)
are provided, and predetermined units of data are stored in each of these columns. The unit of data (Tarapur) is
It is defined as one set of values to be stored in each column. One relation is constructed by an arbitrary number of attributes storing such Tara pulls.

However, in this model, data is stored in the database by specifying a relation name and giving values for each of its attributes. Database searches also specify relations and attributes, and determine whether the value stored there satisfies a predetermined condition with the specified value or the value stored in another attribute. This is done by extracting Tarapuls that satisfy the conditions.

This search condition is given as the values being equal, unequal, smaller, larger, etc. At this time, it is also possible to specify search conditions for each of a plurality of attributes and perform logical processing (AND, OR, etc.) on the results of the condition determination. In history, it is also possible to search a database by specifying multiple relations and searching for a predetermined Tara pull from among multiple relations based on conditions such as the value of the attribute of one relation being equal to the value of the attribute of another relation. It is.

Furthermore, data deletion from the database is basically performed in the same way as J-biped search, but instead of extracting a Tara pull, it is performed by deleting that Tara pull.

Furthermore, the same applies to data updating, which is performed by changing the value of a specified attribute of the obtained Tara pull and storing it.

In addition, each relation is filled with information (person's name, person in charge code), etc. that are permitted to read, add, and change data for each attribute, and measures are taken to protect the data. Note that instead of taking this data protection measure for each attribute, it is also possible to take this measure for each relation.

It should be noted that there may be more than one person's information listed here.

In the relation example shown in FIG. 50, the data is shown as a character string, but the data stored in each relation may also be a simple bit string. In other words, the data stored in the relation may be not only character strings, but also image information, audio information, and the like.

Now, the data accumulated in this database includes the "personal schedule" relation shown in FIG. 50 mentioned above, as well as the "address book" shown in FIG. 51, for example.
1. Individual work and its agents,” “Operation history,” and “Human resources.”
It consists of various relations such as "conference room", "conference room reservation", and "meeting j".

As shown in this example, relations consist of those that are mainly used for personal use and those that are commonly used by many users. Personal relations are established for each workstation used by each individual.
Further, a common relation is provided at a workstation common to multiple users.

Note that a common workstation does not necessarily mean that its hardware is different from other workstations. It goes without saying that a personal workstation may also serve as a common workstation.

Furthermore, the number of common workstations is not limited to one, and a plurality of common workstations may be provided depending on the hierarchical level of the system. In short, a common workstation is set as one that can be easily identified from a plurality of workstations.

Here, the data structure of the "personal schedule" relation shown in FIG. 50 will be briefly explained.

This relation indicates that the relation name is "Personal Schedule" and that it was created by "△△△△". This relation creator “ΔΔΔΔ
” allows all data operations for the relation.

Also, according to the data protection function added to this relation, everyone is allowed to read data, but only "○OO○" and "persons belonging to the engineering department" are allowed to add data. There is. Note that this "person belonging to the technical department" can be found by, for example, referring to the "Personnel" registration page. In addition, the value of "data changes can be made at the level of one person" is r
Permitted only for 5J and above. This "one-person level" refers to personnel relations, for example, (Director; 8) (Deputy Manager; 7) (Section Manager; 6) (Chief; 5)
) etc. to represent the position.

Furthermore, attributes such as r start time, one type of end time, name, and location j are set in this relation, and data is written to each of them.

Next, the physical structure for actually storing the above-mentioned various glue resins in this database section 32 will be explained.

The information storage unit (storage unit) stores a large amount of data, can read and write any part of the data at relatively high speed, and is not expensive at all. is used.

The storage of the database in this information storage unit is determined by setting the storage area of the information storage unit to a specific size, for example, several kilobytes, depending on the length of the data pull, the speed of the computer, etc.)
This is done by dividing each page into sections and managing each page as a page. As shown in FIG. 52, for example, page management information is stored in the 0th page, relation list information is stored in the 1st page, and information on pages in use is stored in the 2nd page.

This list of relations indicates the location of various glue resins in the database.

For example, the actual data stored on the 9th and 11th pages is sorted based on the relation attribute (main attribute) stored on the 5th page, and according to the information on the index page stored on the 10th page. It has become. This index page information indicates in which page the number of attribute values is stored.

When searching data using an attribute other than this main attribute, a second
Via the sub-index of page 0, first the 21st
Obtain the sub-data shown on the page and the 22nd page. This sub-data contains only the attribute values and the above-mentioned main attribute values, and the actual data is determined using the attribute values determined here.

If the amount of actual data is enormous, such as image data or audio data, and some bit errors in the data are not a problem, these actual data may be stored on another inexpensive device such as the optical disk device 32d. The file may be stored in a suitable information storage device. In this case, the 9th page or the 11th page
The actual data page such as the page may store information to that effect and the storage location information of the actual data in the device.

However, additional functions for the takebase constructed in this manner include, for example, automatically discarding unnecessary data. This automatic disposal of unnecessary data is performed by giving additional information to the relation, such as [disposal; allowed/disabled] and [discarding method], and by operating an erase command for each relation at predetermined intervals.

Incidentally, erasing of the table can be performed by determining, for example, whether or not the end time of conference information is before the current time. Therefore, there is no need to add any special functionality to erase such a Tara pull.

Another important additional function is data security. This data preservation function prevents data from becoming corrupted (random or lost) due to, for example, hardware failure or power outage.

Specifically, this data preservation function is realized by duplicating information, writing it to magnetic tape, etc.

In this manner, the database unit 32 classifies and organizes various data for each relation, manages the data on a page-by-page basis, and provides the data to various application systems.

Next, the work environment data collection section 25 will be explained.

The work environment data collection unit 25 collects data on past operation history for the workstation, and provides operation guidance based on this data.

Here, the work environment data collection unit 25 has a command correspondence table that associates commands corresponding to the functions of the information processing system with commands corresponding to the functions of other information systems, as shown in FIG. 53, for example. It is provided.

Specifically, when the information processing system is A, and the other information processing systems are B, C, D, etc., the command of the other system corresponding to the command "DELETE" in system A is "DEL". ERASE""RE
"MOVE" is indicated by the command correspondence table.

Figure 54 analyzes the command input by the user,
This figure shows a schematic configuration of a work environment data collection unit 25 that executes predetermined operations and various guidances.

In this work environment data collection section 25, first, the command inputted from the command input section 25a is sent to the command analysis section 25.
b and is analyzed with reference to the command correspondence table 25c. Specifically, it is checked whether the input command is registered in the command correspondence table 25c according to the procedure flow shown in FIG. That is, when a command is input, it is first checked whether the input command is from system A or not. And the input command is system A
If the command is analyzed as a command, the command analysis unit 25
b gives the input command to the command execution unit 25d and causes it to execute a predetermined operation based on the command.

On the other hand, if the input command is not from system A, it is checked whether it corresponds to a command from another system, and if there is a command associated with it, the corresponding command is displayed on the screen display section 25e. Display at. In other words, if a command is used in another system (system B), for example "DEL", a command "DELETE" to the corresponding system is requested, and this is displayed on the screen display section 25e as operation guidance. I will do it.

Note that if the command corresponding to the input command does not exist in the command correspondence table 25c, the screen display section 2
A command error message is displayed in step 5c.

Specifically, the command input is processed as follows. Now, assume that a user who has experience operating systems B and C operates system A (the information processing system) for the first time. Here, when the user inputs a command to delete the data "ABC", conventionally, the user inputs "DELETE" for data deletion according to the instruction manual of System A.
You need to find a command and enter it.

However, in this case, the user is using the data erasing command "ER" that was used in System C, for example, according to past experience.
ASE ABC" is input as shown in FIG. 56(a).

Then, the work environment data collection unit 25 analyzes this input command, obtains the system A command "DELETE" corresponding to the input command "ERACE" from the command correspondence table 25c, and displays this as a guide. As a result, even when operating System A for the first time, the user knows that the data deletion command is "DELETE" and can erase the data by inputting that command according to the guide. It becomes possible.

In addition, in order to display a list of file names,
) command “DIR” in system B as shown in
When inputting ``CATA'', the corresponding command "CATA" in the system A is similarly determined and displayed as a guide. As a result, following this guide the command “CATA
” will display a list of file names.

By utilizing the functions of the work environment data collection unit 25 in this manner, by inputting a command used in a system with which the user has past operating experience, corresponding commands in that system are displayed as a guide. Therefore, the system user can operate the system by making maximum use of the knowledge acquired in the past. Then, it becomes possible to easily know the commands of the information processing system. Therefore, the user is freed from the trouble of checking the operating manual of the information processing system each time. Therefore, effects such as being able to significantly shorten the time required to learn how to operate the system can be expected.

Incidentally, when a command corresponding to an input command is obtained and displayed as a guide, the command may be executed upon receiving a judgment input of its pass/fail.

That is, the procedure flow is shown in FIG. 57, and the display example is shown in FIG. 58.
ERASE", and when the corresponding deletion command "DELETE" of system A is requested, it is checked whether this is correct or not.

When a positive (Y) instruction input is received, it is determined that the input command indicates "DELETE", and this is sent to the command execution unit 25d to execute the process.

In this way, as soon as the command correspondence is guided and instructed, the desired process is executed according to the input and command, so there is no need to input the correct command again. In other words, an input command is automatically converted into a corresponding command, and the process is executed. Therefore, it is possible to further improve the operability.

Note that any number of compatible commands may exist depending on the type of system. In short, command correspondence table 25
It is sufficient to store them in association with c. It goes without saying that the command is not limited to the above-mentioned character string format.

Next, the collection of system proficiency data by the work environment data collection unit 25 will be explained. Inside the work environment data collection unit 25, an external storage device and a control device are placed as hardware for executing the system proficiency data collection process.

FIG. 59 is a flowchart showing the system proficiency data collection process.

When a user enters their identification code (user number, password, etc.)
When input, the work environment data collection unit 25 obtains a proficiency table corresponding to the identification code from the external storage device and sets it inside the device. This proficiency level table stores the level of proficiency of each user with respect to various functions of the system, and is structured as shown in FIG. 60, for example.

That is, this proficiency table shows, for each function used, the frequency of use, the date and time of last use, the proficiency class for the function declared by the user, the proficiency class when the function was last used,
Furthermore, it is composed of information on the complexity of the function, etc.

Here, the degree of complexity increases as the function to be used requires specialized knowledge, and as the function becomes more advanced than the basic function.

However, such a proficiency table is set up for each user,
Each is stored in an external storage device.

Note that for a user who uses the system for the first time, a proficiency table for that user is created by setting a new identification code and is registered in the external storage device.

Note that, in addition to the above-mentioned proficiency table, messages for each function used corresponding to the proficiency class are registered in the external storage device, as shown in FIG. 61, for example. The lower the proficiency level of the message, the easier it is to understand, including the background explanation. In addition, classes with a high level of proficiency have advanced content that includes simple explanations and introductions to specialized functions.

Also, proficiency classes are, e.g. A; Beginner class B; Intermediate class C; Expert class The classification is set as follows.

When the proficiency table corresponding to the input identification code is obtained, a menu is displayed that allows the user to select the function to be used. For this menu, the user inputs, for example, a number corresponding to the function to be used.

Then, the control device determines whether the input information is an end signal or a selection signal for a function to be used, and if it is a selection signal for a function to be used, the operation is as follows.

That is, when a usage function selection signal is input, first, the aforementioned proficiency table for the user is referred to, and information such as frequency of use, date and time of last use, declared proficiency class, etc., corresponding to the selected usage function is obtained. Desired.

Then, weighting is performed according to this information, and the current proficiency class is determined.

To determine this proficiency class, for example, the frequency of use is P3, the date and time of last use is T, and the current date and time of use is I.
E1 date and time is T 1 user declaration proficiency class is X 1 front entrance usage proficiency class is X2a! (A, B, C1, m miscellaneousness P 1
And when the discriminant function is F, C'F' KP +K (T -T
) r , 1 1 2 c
3 GL [xt] ten N4 G2 [N2 ko + N5 P.

required as. However, in the above formula, K, K.

4 is set to appropriate values by experiment etc. A, B,
This is the evaluation weight for C. These evaluation weights have the following relationships: Y<Y<Y, Z<Z<Z, and are set to appropriate values through experiments or the like.

Here, GI [Xl] means that it takes the value Yl when Xl-A, and takes the value Y2 when N2-B. Moreover, (T − T ) is the number of days from the last used Ce year, month, date and time to the present time converted into hours.

The class determination is performed in the following manner based on the value of the discriminant function Fr described above.

F <N...A class "I N ≦F <N...B class l r
2 N2≦Fr...C class Note that the determination thresholds N and N are appropriately determined based on experiments and the like.

Once the proficiency class is determined in this manner, guide messages and error messages that correspond to the determined proficiency class and correspond to the specified usage function as described above are obtained from the external storage device.

Thereafter, the currently determined proficiency class is compared with the previous proficiency class stored in the proficiency table. If there is a change in the proficiency class, a message indicating that the proficiency level has changed is added to the guide message and written.

This proficiency class change message consists of four types of messages as shown in FIG. 62, for example. Then, it is determined according to the form of the class change and displayed together with the guide message, etc.

The user performs processing operations according to the various messages displayed in this manner.

Specifically, when it is determined that the user is in the beginner class (class A) for the function used to store created data in a file, a message as shown in FIG. 63 is displayed.

If the user makes a mistake in inputting information in spite of this message, an error message as shown in FIG. 64 is displayed, for example, and guidance on how to use the function is provided.

Further, if the user's proficiency level is determined to be intermediate class (B class), a message as shown in FIG. 65 is displayed. If the user makes a mistake in inputting information in spite of this message, an error message as shown in FIG. 66 is displayed, for example, and guidance on how to use the function is provided. Similarly, if the user's proficiency level is determined to be in the expert class (C class),
A message as shown in FIG. 67 is displayed, and if there is an error in the information input, an error message as shown in FIG. 68 is displayed to guide the operation of the function to be used.

However, when data is entered into the blank field of the guide message displayed as described above, the control device adds (+1) to the frequency of use of the proficiency table of the desired user as described above, and Update the year, month, date and time as well as the previous usage proficiency class. Then, the user is prompted to execute the function to be used, and, assuming that the function to be used has been completed, the process returns to the menu display operation for selecting the function to be used.

If the usage function selection signal is input again here, the above-described process will be repeated again.

However, when the termination selection signal is input, the proficiency table created and updated as described above is written into the proficiency file of the external storage device together with the identification code of the corresponding user, and this is saved. Then, the series of processing procedures is completed.

In this way, the work environment data collection unit 25 collects data on proficiency regarding system operations and provides appropriate guidance for the operations based on the collected data.

The above is the basic configuration of this workstation and its functions.

Next, the processing function for selecting an agent in the workstation configured as described above will be explained.

This proxy selection processing function automatically selects an appropriate proxy who can respond to an incoming call, according to the telephone business, etc., when the called party is absent, for example. It is. This processing procedure will be explained below along the processing flow shown in FIG. 69.

When a telephone call is received, the automatic operation function of the control unit 2 is activated, and the voice synthesis unit 2B and the voice recognition unit 19 are activated. Then, the speech synthesis section 26 generates a message such as "This is OO. Who do you need?" and outputs it to the caller of the above-mentioned incoming call.

When the caller receives this and says who has the business,
The telephone voice is input to the voice recognition section 19 and is voice recognized. This voice recognition determines the called party (individual being called) from the telephone voice (step a).

Then, the workstation searches the called person's personal schedule registered in the database section 32 according to the called person's information (step b). Through this individual schedule search, it is determined whether the individual (called party) is present, that is, whether or not he or she can answer the telephone (step C). If the called party is present,
For example, the voice synthesis unit 26 outputs a message such as "I'll connect you now," and transfers the incoming call to the telephone terminal used by the called party (step d). The telephone terminal used by the called party is determined by, for example, obtaining the telephone extension number of the called party from the personnel relations registered in the database section 32.

On the other hand, if the called party is absent and cannot respond to the incoming call (step c), the voice synthesis unit 2
B is activated, and a message indicating that the called party is absent and a message requesting telephone business are outputted by voice (step e). This message output is performed by issuing an inquiry such as ``Mr.

When the caller speaks the business (job name) in response to this arrangement, the telephone voice is recognized, and information about the job (job) is extracted from the input voice information (
Step f). Then, in accordance with the recognized business information, an agent is selected to respond to the incoming call on behalf of the called party.

This selection of the agent is first performed by searching the agent's relations registered in the database section 32, for example as shown in FIG. 51(b) (step g). This agent relationship is the registration of the individual names of individuals who can handle various tasks (requirements) as agents, and if there are multiple agents, the priority order is They are registered in order with . In other words, the names of agents who can handle each task are registered according to the organizational structure of the task, the division of tasks, etc.

From such agent relations, agents corresponding to the requirements of the incoming call described above are searched and extracted in order according to their priorities (step g).

Once the agent is searched and extracted, the personal schedule of the agent is then searched (step h). Then, it is determined whether the agent is actually able to answer the incoming call (step i).

If the location of the agent is clear, the voice synthesizer 26 outputs a message to the effect that the agent is acting as a telephone agent by calling the person's location and forwarding the incoming call (step j
). This message to the effect of telephone acting is composed of a synthesized voice such as, for example, "I have a call regarding △△ to Mr. XX, but please accept the call on my behalf." Through this process, the incoming call is answered by the agent.

On the other hand, if the agent is not present, but it is clear that the agent is nearby (for example, in the same management section), the agent is called using, for example, the zone browsing function of the telephone (step k). When the agent answers from the nearest telephone terminal (step 1'),
A message to the effect of the above-mentioned telephone substitution is conveyed to the substitute, and the incoming call is transferred to the telephone terminal (step m).

On the other hand, if it is determined by the personal schedule search for the agent that the selected agent is absent (step 1), the next ranking agent is found from the relationship of the agent (step n). The above-described process is then repeated for this next-ranked agent, and the incoming call is transferred to the other party.

Note that if all the agents registered in the agent's relationship are unable to receive the incoming call due to absence etc. (step O), the incoming call will not be answered even if the incoming call is answered by another person. Unable to meet requirements. Therefore, in this case, the speech synthesis unit 2B outputs a message to the effect that the person in charge of the business is absent (step p).
.

Through the agent selection procedure described above, an appropriate agent for the incoming call is selected, and the call is transferred to that agent. Therefore, unlike in the past, it is no longer necessary to check organizational charts, work allocation tables, etc. to find agents who can handle the matter one by one. Therefore, while significantly reducing unproductive miscellaneous tasks,
It becomes possible to quickly select an appropriate agent to respond to incoming calls.

Note that the present invention is not limited to the embodiments described above. Although the selection of a proxy for incoming calls to an absentee person has been described here, the reception process can be similarly implemented for selecting a person in charge of a business.

Further, if it is possible to transfer the incoming call to the called party's location, etc., the incoming call can also be transferred. Further, here, the agent is selected from information on the job inputted by voice, but it is also possible to select the agent directly from the personal name of the called party, for example, according to the business organization chart. In addition, the present invention can be implemented with various modifications without departing from the gist thereof.

[Effects of the Invention] As explained above, according to the present invention, for example, when the called party of an incoming call is absent, an agent suitable for responding to the incoming call is quickly assigned according to information on the business, etc. Moreover, it can be automatically selected. Therefore, the unproductive chore of selecting an agent, which used to be done manually, can be greatly reduced, and the appropriate agent can respond quickly.
This has great practical effects, such as facilitating office work and improving work efficiency.

[Brief explanation of the drawing]

The figures show one embodiment of the present invention. Fig. 1 is a diagram showing a schematic configuration of a proxy selection processing function in a workstation according to the present invention, and Fig. 2 is a diagram showing a workstation equipped with this proxy selection processing function. A schematic configuration diagram of the station; Figure 3 is an external view of an IC card attached to the workstation; Figure 4 is an exploded perspective view showing the structure of the IC card; Figure 5 is a diagram showing the structure of the printed circuit board of the IC card. , FIG. 6 is a diagram showing the configuration of the semiconductor integrated circuit section of the IC card, FIG. 7 is a diagram showing the configuration of the encryption processing section in the workstation, FIG. 8 is a diagram showing the concept of encryption/decryption, Figure 9 is a block diagram of the encryption unit, Figure 10 is a block diagram of the decryption unit, Figure 11 is a block diagram of the R5A processing unit, Figure 12 is a diagram showing the configuration of the image matching unit in the workstation, and Figure 13 is a diagram showing the configuration of the image matching unit in the workstation. Figure 14 shows an example of a face to be image-processed, Figure 14 shows the structure of image data, Figure 15 shows the configuration of the voice recognition section in a workstation, and Figure 16 shows the input voice pattern. Figure 17 is a diagram showing the acoustic characteristics of consonants, Figure 18 is a diagram showing an example of a transition network, Figure 19 is a diagram showing the procedure of speech recognition processing, and Figure 20 is a diagram showing input speech. 21 is a diagram showing the learning processing procedure of the speech recognition dictionary. FIG. 22 is a diagram showing the configuration of the first character recognition block of the character recognition unit in the workstation. Figure 23 is a diagram showing an example of a FAX transmission manuscript paper on which characters to be recognized are written, Figure 24 is a diagram to explain the process of cutting out characters to be recognized, and Figure 25 is a diagram showing the second Figure 26 is a diagram showing the configuration of the figure recognition block in the workstation, Figures 27 to 30 are diagrams for explaining figure recognition processing, and Figure 31 is the workstation. FIG. 32 is a diagram showing the configuration of the image recognition unit in FIG.
Figure 33 is a diagram showing an example of processing for an input image;
Figure 4 is a diagram showing feature point detection in a segment, Figure 35 is a diagram showing the configuration of a voice verification unit in a workstation, Figure 36 is a diagram showing an example of band division of a filter bank, and Figure 37 is a diagram showing filter characteristics. Figure 38 is a diagram showing the configuration of the speech synthesis section in the workstation, Figure 39 is a diagram showing the configuration of the rule synthesis parameter generation device, Figure 40 is a diagram showing the speech parameter conversion structure, and Figure 41 is a diagram showing the speech synthesis section. Figure 42 is a diagram showing the configuration of the image composition section in the workstation, Figures 43 and 44 are diagrams showing the concept of image composition processing, and Figure 45 is a diagram showing the configuration of the output format selection section in the workstation. 46 is a diagram showing the flow of output format selection processing procedure, FIG. 47 is a diagram showing the flow of partner station identification processing procedure, FIG. 48 is a diagram showing the structure of the media conversion table, and FIG. 49 is a diagram showing the structure of the media conversion table. Figure 50 shows the configuration of the database section in the workstation, Figure 50 shows the data structure of the database, Figure 51 shows an example of relations, and Figure 5
Figure 2 shows the structure of the relation, Figure 53 shows the structure of the command correspondence table, and Figure 5 shows the structure of the command correspondence table.
Figure 4 is a diagram showing the configuration of the work environment data collection unit in the workstation, Figures 55 to 58 are diagrams for explaining the processing of the command unit, and Figure 59 is a diagram showing the flow of the system proficiency data collection process. Figure 60 is a diagram showing the structure of the proficiency table, Figures 61 to 68 are diagrams for explaining the processing of the work environment data collection unit, and Figure 69 is the substitute selection process in this workstation. It is a diagram showing the flow of procedures. ■...Bus, 2...Control unit, 3...Image input device, 4...Position input device, 5...Audio input unit, 6
...Keyboard part, 7...IC card part, 8...
Bus controller, 9...Audio output device, 10...
Display unit, 11... image output device, 12.
13...Communication device, 14...Switching device, 15...
・Timer part, 16... Encryption processing unit, 17... Voice matching unit, 18... Image matching unit, 19... Voice recognition unit, 20... Voice analysis unit, 21... Character recognition unit, 22... Graphic recognition unit, 23... Image recognition unit,
24... Output format selection unit, 25... Working environment data collection unit, 26... Voice synthesis unit, 27... Image synthesis unit, 28... Graphic synthesis unit, 29... Audio compression・
Expansion section, 30... Image compression/expansion section, 31...
- Signal processing unit, 32...database unit. Patent Attorney Patent Attorney Takehiko Penko Figure 1 #I45 Figure 6 Figure 4 v Figure 47 (encoded) 1 t (No. 11) Figure 8 Figure 9 Figure 10 (41!;k ) Figure 11 Figure 12 Figure 13 Figure 14 Figure 17 Figure 19 Figure 20 Figure 25 Figure 26 Figure 27 Figure 28 Figure 29 Figure 30 Figure 31 Figure 33 Figure 37 CM Figure 38 * 39 Figure 40 Figure 41 Figure 42 Figure 43 Figure 49 Figure 52 Figure 60 Figure 61 Figure 63 Figure 64 Figure 65 Figure 66

Claims (6)

[Claims] (1) An information storage device that stores information indicating the correlation between information that identifies multiple individuals and information related to business content as an agent relation, and the above-mentioned information according to the information related to the individual or business content specified by the input information. 1. An intelligent workstation characterized by comprising means for searching a storage device for information on an individual that can correspond to the input. (2) The search of the information storage device is performed when the individual specified by the input information is unable to respond to the input, and the information storage device according to claim 1 is searched for an agent for the specified individual. workstation. (3) Searching the information storage device determines the business content from the business indicated by the input information, and searches for individuals or their agents who can deal with the business according to the determined business content information. An intelligent workstation according to claim 1. (4) The intelligent workstation according to claim 1, wherein the input information is input via communication means. (5) Agent information stored in the information storage device is registered by prioritizing multiple agents for a specific individual, and is searched and extracted in order of priority. 2. An intelligent workstation according to claim 1, wherein the intelligent workstation is an intelligent workstation. (6) A patent claim in which the determination of whether or not a designated individual or a searched agent can handle the input is made by searching the personal schedule stored in the information storage device of that individual. Intelligent workstation according to scope 1.